Add Model
guoqingbao/xinfer
Adapt and port new LLM model architectures to this xinfer project.
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
Install Qwen Mtp Gguf
$ npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install R6410418/Jackrong-llm-finetuning-guide qwen-mtp-gguf --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/R6410418/Jackrong-llm-finetuning-guide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/qwen-mtp-gguf .claude/skills/qwen-mtp-gguf && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "qwen-mtp-gguf" agent skill from https://github.com/R6410418/Jackrong-llm-finetuning-guide/tree/main/qwen-mtp-gguf into .claude/skills/qwen-mtp-gguf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-mtp-gguf", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/R6410418/Jackrong-llm-finetuning-guide/tree/main/qwen-mtp-ggufType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install R6410418/Jackrong-llm-finetuning-guide qwen-mtp-gguf --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/R6410418/Jackrong-llm-finetuning-guide.git skills-src && mkdir -p .agents/skills && cp -r skills-src/qwen-mtp-gguf .agents/skills/qwen-mtp-gguf && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "qwen-mtp-gguf" agent skill from https://github.com/R6410418/Jackrong-llm-finetuning-guide/tree/main/qwen-mtp-gguf into .agents/skills/qwen-mtp-gguf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-mtp-gguf", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install R6410418/Jackrong-llm-finetuning-guide qwen-mtp-gguf --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/R6410418/Jackrong-llm-finetuning-guide.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/qwen-mtp-gguf .cursor/skills/qwen-mtp-gguf && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "qwen-mtp-gguf" agent skill from https://github.com/R6410418/Jackrong-llm-finetuning-guide/tree/main/qwen-mtp-gguf into .cursor/skills/qwen-mtp-gguf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-mtp-gguf", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/R6410418/Jackrong-llm-finetuning-guide.git --path qwen-mtp-gguf--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install R6410418/Jackrong-llm-finetuning-guide qwen-mtp-gguf --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/R6410418/Jackrong-llm-finetuning-guide.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/qwen-mtp-gguf .gemini/skills/qwen-mtp-gguf && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "qwen-mtp-gguf" agent skill from https://github.com/R6410418/Jackrong-llm-finetuning-guide/tree/main/qwen-mtp-gguf into .gemini/skills/qwen-mtp-gguf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-mtp-gguf", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install R6410418/Jackrong-llm-finetuning-guide qwen-mtp-ggufInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/R6410418/Jackrong-llm-finetuning-guide.git skills-src && mkdir -p .github/skills && cp -r skills-src/qwen-mtp-gguf .github/skills/qwen-mtp-gguf && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "qwen-mtp-gguf" agent skill from https://github.com/R6410418/Jackrong-llm-finetuning-guide/tree/main/qwen-mtp-gguf into .github/skills/qwen-mtp-gguf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-mtp-gguf", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install R6410418/Jackrong-llm-finetuning-guide qwen-mtp-gguf --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/R6410418/Jackrong-llm-finetuning-guide.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/qwen-mtp-gguf .opencode/skills/qwen-mtp-gguf && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "qwen-mtp-gguf" agent skill from https://github.com/R6410418/Jackrong-llm-finetuning-guide/tree/main/qwen-mtp-gguf into .opencode/skills/qwen-mtp-gguf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qwen-mtp-gguf", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
qwen-mtp-gguf- GitHub stars
- 1.7k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 659 words
- Files
- 18 (incl. scripts, references)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
- Works in 6 steps: Identify the target model and matching… → Preflight the environment, disk, RAM,… → Ask the user to choose upload strategy… → …
- Another coding agent needs to inspect a users machine
- SKILL.md covers Operating Principle, Required User Inputs, Upload Strategy Choice and Environment Bootstrap, plus 5 more sections
- Runs Python and Shell scripts from its folder; calls python3 and bash; needs HF_TOKEN
What it does
Qwen Mtp Gguf is an agent skill from R6410418/Jackrong-llm-finetuning-guide. Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release. Use when Codex or another coding agent needs to inspect a user's machine, estimate disk/RAM requirements from Hugging Face model sizes and requested quant formats, bootstrap llama.cpp and Python dependencies, extract MTP heads from a matching official/base Qwen model, merge them into a fine-tuned or target safetensors model, run local HF/GGUF smoke tests with Qwen chat formatting, quantize to GGUF, and optionally upload or…
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files, including scripts and reference files (for example `README.md`, `agents/openai.yaml` and `docs/Qwen-MTP-GGUF-Agent-Usage.md`).
It sits in AI & LLM Engineering, covering QA and bug reports, LLM inference and serving and Model hubs and datasets. It works with llama.cpp, Qwen, Hugging Face and Python. The licence is MIT.
When your agent uses it
- Another coding agent needs to inspect a users machine
- Estimate disk/RAM requirements from Hugging Face model sizes and requested quant formats
- Bootstrap llama.cpp and Python dependencies
- Extract MTP heads from a matching official/base Qwen model
Example prompts
- “/qwen-mtp-gguf”
Requirements
- Python 3
- A Bash shell
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Identify the target model and matching MTP source model.
- Preflight the environment, disk, RAM, tools, token access, and config compatibility.
- Ask the user to choose upload strategy when it affects disk use.
- Prepare the target HF directory and inject only missing MTP/nextn tensors.
- Convert to a temporary F16 GGUF, smoke-test locally, then quantize.
- Upload with resume support, or keep local artifacts if the user chooses local-only.
What it can do on your machine
Read from SKILL.md and the folder at commit ef2b17f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Python and Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3bash
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
HF_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Qwen Mtp Gguf loads about 1.7k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 140 tokens; SKILL.md has 659 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from R6410418/Jackrong-llm-finetuning-guide at commit ef2b17f, republished under its MIT licence (© R6410418). 659 words, ~1,676 tokens.
Download SKILL.mdSave it as
.claude/skills/qwen-mtp-gguf/SKILL.md (or your agent's skills folder). This skill also uses 17 other files; get the full folder from GitHub.- name
- qwen-mtp-gguf
- description
- Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release. Use when Codex or another coding agent needs to inspect a user's machine, estimate disk/RAM requirements from Hugging Face model sizes and requested quant formats, bootstrap llama.cpp and Python dependencies, extract MTP heads from a matching official/base Qwen model, merge them into a fine-tuned or target safetensors model, run local HF/GGUF smoke tests with Qwen chat formatting, quantize to GGUF, and optionally upload or resume Hugging Face releases.
Qwen MTP GGUF
Operating Principle
Run this as a staged release pipeline, not a blind conversion:
- Identify the target model and matching MTP source model.
- Preflight the environment, disk, RAM, tools, token access, and config compatibility.
- Ask the user to choose upload strategy when it affects disk use.
- Prepare the target HF directory and inject only missing MTP/nextn tensors.
- Convert to a temporary F16 GGUF, smoke-test locally, then quantize.
- Upload with resume support, or keep local artifacts if the user chooses local-only.
MTP/GGUF conversion and llama.cpp quantization do not require a GPU. GPU acceleration can make later inference tests faster, but the default smoke test should use CPU mode (-ngl 0) so it works on common machines.
Required User Inputs
Ask for missing items only when they cannot be inferred safely:
- Target model: HF repo ID or local HF model directory.
- Matching MTP source model: the official/base Qwen-family repo with the same architecture, size, tokenizer, and MTP layout.
- Output mode: local-only, stream upload, or batch upload.
- Output repo ID when uploading.
- Quantization formats. Default full matrix:
q2_k,q3_k_s,q3_k_m,q3_k_l,iq4_xs,q4_k_s,q4_k_m,q5_k_s,q5_k_m,q6_k,q8_0,bf16.
If the target and MTP source configs disagree on core architecture fields, stop and ask before continuing.
Upload Strategy Choice
When the user has not specified a strategy, explain the tradeoff briefly and ask:
stream: quantize one GGUF, upload it, then delete it. Lowest peak disk use and best default for large models.batch: quantize everything first, then upload. Useful when network is unstable but requires much more disk.local-only: prepare all GGUF files locally without uploading.
Use stream when the user asks for a full large-model release and does not care about keeping local copies.
Environment Bootstrap
Use scripts/bootstrap_qwen_mtp_env.sh when llama.cpp or Python dependencies are missing.
bash scripts/bootstrap_qwen_mtp_env.sh --prefix ./qwen-mtp-env --backend cpu
source ./qwen-mtp-env/.venv/bin/activateBackend options are cpu, cuda, metal, and vulkan. Prefer cpu unless the user explicitly wants accelerated smoke tests or already has a configured GPU toolchain.
Preflight
Always run preflight before downloading large model weights:
python3 scripts/qwen_mtp_gguf_pipeline.py \
--source-repo owner/target-qwen-finetune \
--mtp-source-repo owner/matching-base-qwen-with-mtp \
--output-repo owner/target-qwen-mtp-gguf \
--work-root ./mtp-gguf-work \
--llama-cpp ./qwen-mtp-env/llama.cpp \
--token-env HF_TOKEN \
--upload-strategy stream \
--preflight-onlyReview preflight_report.md before running. It reports:
- OS, CPU cores, total RAM, detected GPU hint, Python version.
- Required commands and packages.
- llama.cpp converter, quantizer, and
llama-clistatus. - Target model size from HF file metadata or local files.
- Minimal MTP shard download size.
- Estimated F16/BF16 and quantized GGUF sizes.
- Required free disk with a safety factor.
- Recommended RAM and config mismatch warnings.
Show full SKILL.md (275 more words)Show less
Full Pipeline
python3 scripts/qwen_mtp_gguf_pipeline.py \
--source-repo owner/target-qwen-finetune \
--mtp-source-repo owner/matching-base-qwen-with-mtp \
--output-repo owner/target-qwen-mtp-gguf \
--work-root ./mtp-gguf-work \
--llama-cpp ./qwen-mtp-env/llama.cpp \
--filename-prefix target-qwen-MTP \
--token-env HF_TOKEN \
--upload-strategy stream \
--private \
--smoke-test-before-upload \
--cleanup-after-uploadThe pipeline:
- Downloads or copies the target HF model.
- Detects existing MTP/nextn tensors and validates index mappings.
- Downloads only the MTP source shards listed in the source index.
- Saves
mtp_heads.safetensors, updatesmodel.safetensors.index.json, and validates all new keys. - Converts F16 for quantization and BF16 directly from the prepared HF directory.
- Runs GGUF smoke tests before upload when enabled. Prefer the model's embedded chat template when llama.cpp supports it; use ChatML only as a minimal fallback for load/generation sanity checks.
- Lists remote HF files before upload and skips completed GGUFs on resume.
- Deletes local GGUF files only after confirmed upload when cleanup is enabled.
Smoke Tests
Use the GGUF smoke test for release validation:
python3 scripts/qwen_gguf_smoke_test.py \
--model ./mtp-gguf-work/target-qwen-MTP-GGUF/target-qwen-MTP-Q8_0.gguf \
--llama-cli ./qwen-mtp-env/llama.cpp/build/bin/llama-cli \
--prompt "State the capital of France in one short sentence." \
--gpu-layers 0Use the HF smoke test only when the machine can load the HF model:
python3 scripts/qwen_hf_smoke_test.py \
--model ./mtp-gguf-work/target-qwen-MTP-HF \
--prompt "Write one concise sentence about MTP inference."For Qwen-family chat formatting, use apply_chat_template(..., add_generation_prompt=True, tokenize=False) on the HF side. For GGUF, prefer the chat template embedded by llama.cpp conversion or copied from tokenizer_config.json; use raw ChatML only as a fallback smoke test, not as the quality/reasoning benchmark template.
Agent Compatibility
This skill is Codex-native, but the workflow is intentionally agent-agnostic:
- Claude Code, Codex, OpenCode, Qwen Code, Hermes, and similar agents can run the same scripts from a shell.
- The agent should call
--preflight-only, summarize blockers, ask for the upload strategy if needed, then run the full command. - Keep user-specific tokens, paths, private repo names, and logs out of public PRs and model cards.
References
- Read
references/environment-and-sizing.mdbefore changing preflight logic or resource thresholds. - Read
references/technical-flow.mdbefore changing extraction, injection, conversion, or upload behavior. - Read
references/agent-integration.mdwhen packaging this for another agent framework. - Read
references/troubleshooting.mdwhen conversion, tensor lookup, disk, RAM, or upload steps fail.
© R6410418, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 17 other files (scripts, references) in qwen-mtp-gguf of R6410418/Jackrong-llm-finetuning-guide.
- SKILL.md
- .gitignore
- LICENSE
- README.md
- agents/openai.yaml
- docs/Qwen-MTP-GGUF-Agent-Usage.md
- docs/Qwen-MTP-GGUF-Pipeline-Guide.md
- docs/Qwen-MTP-GGUF-Skill-README.md
- env.example
- jobs.example.json
- references/agent-integration.md
- references/environment-and-sizing.md
- references/technical-flow.md
- references/troubleshooting.md
- scripts/bootstrap_qwen_mtp_env.sh
- scripts/qwen_gguf_smoke_test.py
- scripts/qwen_hf_smoke_test.py
- … and 1 more
Open the folder on GitHubat commit ef2b17f
Compare with similar skills
Qwen Mtp Gguf next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Qwen Mtp Gguf this skillR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Add Modelguoqingbao/xinfer | 334 | — | ~4.2k | Automated safety check: Notes | MIT | |
| Resolvealexziskind1/model-shelf | 130 | — | ~792 | Automated safety check: Pass | MIT | |
| Test Modelguoqingbao/xinfer | 334 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Aqua Model Lifecycleoracle/accelerated-data-science | 125 | — | ~1.4k | Automated safety check: Pass | UPL-1.0 | |
| Hugging Face Local Modelshuggingface/skills | 11k | 3 repos | ~945 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Resolve
alexziskind1/model-shelf
Always resolve Hugging Face models via model-shelf before any download.
Test Model
guoqingbao/xinfer
Test LLM models served by xinfer for correctness, output quality, and performance.
- Official
Aqua Model Lifecycle
oracle/accelerated-data-science
Register, list, get, and manage LLM models in OCI AI Quick Actions (AQUA) using the ADS SDK.
- Official
Hugging Face Local Models
huggingface/skills
Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.
Edge Bringup
exeex/edge-cores
Prepare a macOS or Ubuntu machine for edge-e3 development, diagnose missing Verilator/LLVM/Python dependencies, initialize the public repository, and answer or act on the example prompts in the root…
More from R6410418/Jackrong-llm-finetuning-guide
Qwopus27b Rl Training
R6410418/Jackrong-llm-finetuning-guide
Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.
GitHub Sync Gate
R6410418/Jackrong-llm-finetuning-guide
Enforce this repository's local-review-first GitHub sync policy.
Qwen Mtp Gguf Release
R6410418/Jackrong-llm-finetuning-guide
Repository-level wrapper for the canonical Qwen MTP or nextn GGUF release workflow.
Repository Resource Portal
R6410418/Jackrong-llm-finetuning-guide
Maintain this repository as a growing educational LLM knowledge base.
Related
Works with
Categories
Questions about Qwen Mtp Gguf
What does Qwen Mtp Gguf do?
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release. Qwen Mtp Gguf is an agent skill from R6410418/Jackrong-llm-finetuning-guide. Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
When should I use Qwen Mtp Gguf?
Qwen Mtp Gguf fits situations like: another coding agent needs to inspect a users machine; estimate disk/RAM requirements from Hugging Face model sizes and requested quant formats; bootstrap llama.cpp and Python dependencies; extract MTP heads from a matching official/base Qwen model.
How do I install Qwen Mtp Gguf in Claude Code?
Run `npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a claude-code`. Or copy the skill folder (qwen-mtp-gguf in R6410418/Jackrong-llm-finetuning-guide) into .claude/skills/qwen-mtp-gguf in your project. Claude Code loads it when a task matches its description.
How do I install Qwen Mtp Gguf in Codex?
Run `npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a codex`. Or copy the skill folder (qwen-mtp-gguf in R6410418/Jackrong-llm-finetuning-guide) into .agents/skills/qwen-mtp-gguf in your project. Codex loads it when a task matches its description.
Can I use Qwen Mtp Gguf in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add R6410418/Jackrong-llm-finetuning-guide --skill qwen-mtp-gguf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qwen-mtp-gguf, .gemini/skills/qwen-mtp-gguf, .github/skills/qwen-mtp-gguf and .opencode/skills/qwen-mtp-gguf in your project.
What does Qwen Mtp Gguf need to run?
Going by SKILL.md and its folder, Qwen Mtp Gguf needs Python and a shell for the scripts in its folder, the command-line tools its instructions call (python3 and bash) and credentials named HF_TOKEN. Our summary lists: Python 3; A Bash shell.
Does Qwen Mtp Gguf access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Qwen Mtp Gguf safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Qwen Mtp Gguf use?
Qwen Mtp Gguf is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Qwen Mtp Gguf use?
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.
What are the alternatives to Qwen Mtp Gguf?
Skills that share tags, products or a category with Qwen Mtp Gguf: Add Model (guoqingbao/xinfer, 334 stars), Resolve (alexziskind1/model-shelf, 130 stars), Test Model (guoqingbao/xinfer, 334 stars) and Aqua Model Lifecycle (oracle/accelerated-data-science, 125 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Qwen Mtp Gguf?
R6410418 (a GitHub user) maintains it in R6410418/Jackrong-llm-finetuning-guide, which has 1,709 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 11, 2026.
Source: R6410418/Jackrong-llm-finetuning-guide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.