New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hf Bf16 Gguf Conversion Jobs

by Mesh-LLM in Mesh-LLM/mesh-llm

A skill your agent uses when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the…

Apache-2.0Auto-check passedAI & LLM Engineering

Install Hf Bf16 Gguf Conversion Jobs

skills CLI
$ npx skills add Mesh-LLM/mesh-llm --skill hf-bf16-gguf-conversion-jobs -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Mesh-LLM/mesh-llm hf-bf16-gguf-conversion-jobs --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/hf-bf16-gguf-conversion-jobs .claude/skills/hf-bf16-gguf-conversion-jobs && rm -rf skills-src

Use ~/.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/

Facts

Skill name
hf-bf16-gguf-conversion-jobs
GitHub stars
3.5k
Token cost
~1.1k tokens
SKILL.md length
322 words
Files
2
Skills in repo
25
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the…

  • Converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs
  • SKILL.md covers Preconditions, Local Workflow, HF Jobs Workflow and Monitoring, plus 1 more section
  • Calls hf and just; needs HF_TOKEN
  • A local machine

What it does

Hf Bf16 Gguf Conversion Jobs is an agent skill from Mesh-LLM/mesh-llm. Use when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the artifact to Hugging Face.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in AI & LLM Engineering, covering Model hubs and datasets. It works with llama.cpp and Hugging Face. The repository describes itself as: Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. The licence is Apache-2.0.

When your agent uses it

  • Converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs
  • A local machine
  • Then publishing the artifact to Hugging Face

Example prompts

  • “/hf-bf16-gguf-conversion-jobs”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 1b9f0cf. 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

    Shell commands in SKILL.md call:

    • hf
    • just

    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

Hf Bf16 Gguf Conversion Jobs loads about 1.1k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Mesh-LLM/mesh-llm at commit 1b9f0cf, republished under its Apache-2.0 licence (© Mesh-LLM). 322 words, ~1,135 tokens.

Download SKILL.mdSave it as .claude/skills/hf-bf16-gguf-conversion-jobs/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
hf-bf16-gguf-conversion-jobs
description
Use when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the artifact to Hugging Face.
metadata.short-description
Convert HF checkpoints to BF16 GGUF repos

HF BF16 GGUF Conversion Jobs

Use this skill when the source artifact is a Hugging Face checkpoint repo and the target artifact is a split BF16 GGUF model repo. The operational tool is skippy-quantize; do not use convert_hf_to_gguf.py, hf_to_gguf.py, or a wrapper that shells out to either script. Treat hf_to_gguff.py as the same forbidden path if it appears in old notes or logs.

Preconditions

  • Confirm the source checkpoint repo, revision, tokenizer files, target repo, output basename, expected split count, and desired split size before spending HF Jobs credits.
  • Build the standalone binary with just skippy-quantize-standalone-release-build for local runs or in the job image/script for HF Jobs.
  • Use --output-type bf16 unless the experiment explicitly records a different target precision.
  • Prefer a split output with --window-size 1 for first full-model runs. Raise the window only after a smaller fixture proves the memory and I/O budget.
  • Publish only complete windows, write per-window records, and resume from the first missing target shard after cancellation.

Local Workflow

Create a manifest:

bash
target/release/skippy-quantize init-convert \
  --source /path/to/checkpoint \
  --target /path/to/output-repo \
  --target-prefix BF16 \
  --output-basename <model>-BF16 \
  --output-type bf16 \
  --expected-splits <N> \
  --window-size 1 \
  --manifest /tmp/skippy-convert.json

Dry-run the next conversion window before spending I/O:

bash
target/release/skippy-quantize convert-job \
  --source /path/to/checkpoint \
  --target /path/to/output-repo \
  --target-prefix BF16 \
  --output-basename <model>-BF16 \
  --output-type bf16 \
  --expected-splits <N> \
  --window-size 1 \
  --manifest /tmp/skippy-convert.json \
  --max-memory 32G \
  --dry-run

Run until complete:

bash
target/release/skippy-quantize run-convert \
  --manifest /tmp/skippy-convert.json \
  --max-memory 32G \
  --split-max-size 50G \
  --stream-buffer-bytes 8388608 \
  --spool-dir /tmp/skippy-convert-output \
  --record-dir /tmp/skippy-convert-records \
  --json-event-file /tmp/skippy-convert-status.json \
  --json-event-interval-seconds 120 \
  --json-event-window 8

Validate and publish:

bash
target/release/skippy-quantize verify-job \
  --manifest /tmp/skippy-convert.json \
  --json

hf repo create <org>/<target-repo> --type model --private
hf upload <org>/<target-repo> /path/to/output-repo . --repo-type model

HF Jobs Workflow

Mount the source checkpoint and target model repo rather than downloading the whole checkpoint into the job filesystem:

bash
hf jobs uv run \
  --namespace meshllm \
  --flavor cpu-upgrade \
  --timeout 3d \
  --secrets HF_TOKEN \
  --volume hf://models/<source-repo>:/mnt/checkpoint \
  --volume hf://models/<target-repo>:/mnt/target \
  --env SKIPPY_QUANTIZE_OUTPUT=json \
  --env PYTHONUNBUFFERED=1 \
  --detach \
  /path/to/skippy_convert_job.py \
  -- \
  --source /mnt/checkpoint \
  --target /mnt/target \
  --target-prefix BF16 \
  --output-basename <model>-BF16 \
  --expected-splits <N> \
  --split-max-size 50G \
  --max-memory 32G

The job script should only build or install skippy-quantize, create the manifest if missing, run run-convert, verify the job, and upload sidecars. It must not call the old Python converter.

Monitoring

Use both HF Jobs status and skippy-quantize status:

bash
hf jobs inspect <job-id> --namespace meshllm
hf jobs logs <job-id> --namespace meshllm --tail 120
target/release/skippy-quantize status --manifest /tmp/skippy-convert.json --json

For agents, prefer polling /tmp/skippy-convert-status.json over ingesting full logs. Healthy snapshots show phase movement through running, publishing, and complete, with only the last few high-level events retained. Stop and diagnose if the same window restarts without a new published shard or memory stays pinned near the hardware limit.

Record Keeping

Record the job id, exact command, source revision, target repo commit, split count, split size, memory budget, tokenizer notes, and follow-ups in the experiment card or phase iteration card before promoting the artifact.

© Mesh-LLM, Apache-2.0. 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 1 other file in .agents/skills/hf-bf16-gguf-conversion-jobs of Mesh-LLM/mesh-llm.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 1b9f0cf

Compare with similar skills

Hf Bf16 Gguf Conversion Jobs 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.

Hf Bf16 Gguf Conversion Jobs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hf Bf16 Gguf Conversion Jobs this skillMesh-LLM/mesh-llm3.5k—~1.1kAutomated safety check: PassApache-2.0
Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide1.7k—~1.7kAutomated safety check: PassMIT
Hugging Face LLM Trainerhuggingface/skills11k1 repos~7.2kAutomated safety check: PassApache-2.0
Hugging Face Local Modelshuggingface/skills11k3 repos~945Automated safety check: PassApache-2.0
Add Modelguoqingbao/xinfer334—~4.2kAutomated safety check: NotesMIT
Huggingface LLM Trainerwaybarrios/opencode-power-pack534—~3kAutomated safety check: PassApache-2.0

Similar skills

  • Qwen Mtp Gguf

    R6410418/Jackrong-llm-finetuning-guide

    Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

    1.7k GitHub stars~1.7k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Hugging Face LLM Trainer

    huggingface/skills

    Official

    Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.

    11k GitHub starsUsed in 1 repo~7.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Models

    huggingface/skills

    Official

    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.

    11k GitHub starsUsed in 3 repos~945 tokens
    AI & LLM EngineeringAuto-check passed

  • Add Model

    guoqingbao/xinfer

    Adapt and port new LLM model architectures to this xinfer project.

    334 GitHub stars~4.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Huggingface LLM Trainer

    waybarrios/opencode-power-pack

    Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion.

    534 GitHub stars~3k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

  • Resolve

    alexziskind1/model-shelf

    Always resolve Hugging Face models via model-shelf before any download.

    130 GitHub stars~792 tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from Mesh-LLM/mesh-llm

All 25 skills in this repo

  • Release Validation

    Mesh-LLM/mesh-llm

    A skill your agent uses when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally…

    3.5k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Benchmark Tune

    Mesh-LLM/mesh-llm

    A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…

    3.5k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Config Settings Management

    Mesh-LLM/mesh-llm

    A skill your agent uses when adding, renaming, removing, validating, or exposing mesh-llm config settings, including built-in settings, plugin config schemas, owner-control apply behavior, CLI…

    3.5k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Connect Agents

    Mesh-LLM/mesh-llm

    A skill your agent uses when connecting agent tools or OpenAI clients to mesh-llm — launching or configuring Goose, Claude Code, OpenCode, Pi, curl, or any OpenAI-compatible client against a local…

    3.5k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Hf Gguf Quant Jobs

    Mesh-LLM/mesh-llm

    A skill your agent uses when creating, monitoring, validating, or documenting low-memory Hugging Face Jobs or local runs that quantize split BF16/FP16 GGUF model repos into custom quant GGUF repos…

    3.5k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • Hf Layer Package Jobs

    Mesh-LLM/mesh-llm

    A skill your agent uses when changing mesh-llm automation or CLI flows that discover Hugging Face GGUF models, plan CPU Hugging Face Jobs for layer-package splitting, estimate max cost, or publish…

    3.5k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Hf Bf16 Gguf Conversion Jobs

What does Hf Bf16 Gguf Conversion Jobs do?

A skill your agent uses when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the…. Hf Bf16 Gguf Conversion Jobs is an agent skill from Mesh-LLM/mesh-llm. Use when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the artifact to Hugging Face.

When should I use Hf Bf16 Gguf Conversion Jobs?

Hf Bf16 Gguf Conversion Jobs fits situations like: converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs; A local machine; then publishing the artifact to Hugging Face.

How do I install Hf Bf16 Gguf Conversion Jobs in Claude Code?

Run `npx skills add Mesh-LLM/mesh-llm --skill hf-bf16-gguf-conversion-jobs -a claude-code`. Or copy the skill folder (.agents/skills/hf-bf16-gguf-conversion-jobs in Mesh-LLM/mesh-llm) into .claude/skills/hf-bf16-gguf-conversion-jobs in your project. Claude Code loads it when a task matches its description.

How do I install Hf Bf16 Gguf Conversion Jobs in Codex?

Run `npx skills add Mesh-LLM/mesh-llm --skill hf-bf16-gguf-conversion-jobs -a codex`. Or copy the skill folder (.agents/skills/hf-bf16-gguf-conversion-jobs in Mesh-LLM/mesh-llm) into .agents/skills/hf-bf16-gguf-conversion-jobs in your project. Codex loads it when a task matches its description.

Can I use Hf Bf16 Gguf Conversion Jobs 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 Mesh-LLM/mesh-llm --skill hf-bf16-gguf-conversion-jobs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hf-bf16-gguf-conversion-jobs, .gemini/skills/hf-bf16-gguf-conversion-jobs, .github/skills/hf-bf16-gguf-conversion-jobs and .opencode/skills/hf-bf16-gguf-conversion-jobs in your project.

What does Hf Bf16 Gguf Conversion Jobs need to run?

Going by SKILL.md and its folder, Hf Bf16 Gguf Conversion Jobs needs the command-line tools its instructions call (hf and just) and credentials named HF_TOKEN. Our summary lists: Python 3.

Does Hf Bf16 Gguf Conversion Jobs 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 Hf Bf16 Gguf Conversion Jobs 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. Review the folder before installing.

What licence does Hf Bf16 Gguf Conversion Jobs use?

Hf Bf16 Gguf Conversion Jobs is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hf Bf16 Gguf Conversion Jobs use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hf Bf16 Gguf Conversion Jobs?

Skills that share tags, products or a category with Hf Bf16 Gguf Conversion Jobs: Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars), Hugging Face LLM Trainer (huggingface/skills, 11k stars), Hugging Face Local Models (huggingface/skills, 11k stars) and Add Model (guoqingbao/xinfer, 334 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hf Bf16 Gguf Conversion Jobs?

Mesh-LLM (a GitHub organization) maintains it in Mesh-LLM/mesh-llm, which has 3,495 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 11, 2026.

Source: Mesh-LLM/mesh-llm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.