Quark Torch Model Intake

What it does

When your agent uses it

• The user needs model path validation
• Architecture detection
• Quantization target discovery
• Risk assessment

Example prompts

• “analyze my model”
• “check this model”
• “what architecture is this”
• “/quark-torch-model-intake”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm model source: Is it a local directory or a HuggingFace ID? Check if quark-workspace-validate already confirmed the path.
2. 2Read config: Extract architecture facts from config.json. Present a summary table to the user.
3. 3Assess compatibility: Check model type against Quark's template list. Flag any transformer version requirements.
4. 4Identify risks: Note anything that could affect downstream PTQ planning.
5. 5Emit: Write model_analysis.json. Surface any new constraints back to quark-torch-router so they land in session_context.json.

What it can do on your machine

Read from SKILL.md and the folder at commit 313cb0b. 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:

  • python3

  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 no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Quark Torch Model Intake loads about 2k tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 605 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~121

When it runs · the whole SKILL.md, loaded when a task matches

~2k

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

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 amd/Quark at commit 313cb0b, republished under its MIT licence (© amd). 605 words, ~1,976 tokens.

name

quark-torch-model-intake

description

Inspect a target model and prepare metadata for Quark PTQ planning. Use when the user needs model path validation, architecture detection, quantization target discovery, layer counting, risk assessment, or transformer compatibility checks before planning PTQ. Trigger for "analyze my model", "check this model", "what architecture is this", "can Quark quantize X", "is this model supported", or when any quantization step needs model facts that are missing.

layer

l1-atomic

primary_artifact

model_analysis.json

source_knowledge

examples/torch/language_modeling/llm_ptq/quantize_quark.py, quark/torch/utils/llm/model_preparation.py, quark/torch/quantization/config/template.py

{
  "analysis_status": "complete",
  "model": {
    "model_path": "Qwen/Qwen3-8B",
    "model_type": "qwen3",
    "trust_remote_code": false,
    "transformers_version_required": ">=4.48.0,<5.3",
    "loading_class": "AutoModelForCausalLM",
    "is_moe": false,
    "num_hidden_layers": 36,
    "hidden_size": 4096,
    "estimated_size_gb": 16.0
  },
  "quantization_targets": {
    "linear_layer_count": 224,
    "has_non_linear_experts": false,
    "exclude_defaults": ["lm_head"],
    "needs_moe_preparation": false
  },
  "risks": [
    {
      "severity": "low",
      "message": "Model size fits in single GPU with 24GB+ VRAM for FP8/INT8 schemes.",
      "recovery_hint": "Use --multi_gpu for INT4 with large calibration datasets if OOM occurs."
    }
  ]
}

python3 -c "
from transformers import AutoConfig
import json
config = AutoConfig.from_pretrained('<MODEL_PATH>', trust_remote_code=True)
info = {
    'model_type': config.model_type,
    'num_hidden_layers': config.num_hidden_layers,
    'hidden_size': config.hidden_size,
    'intermediate_size': getattr(config, 'intermediate_size', None),
    'num_attention_heads': config.num_attention_heads,
    'num_key_value_heads': getattr(config, 'num_key_value_heads', None),
    'vocab_size': config.vocab_size,
    'num_experts': getattr(config, 'num_local_experts', getattr(config, 'num_experts', None)),
    'torch_dtype': str(getattr(config, 'torch_dtype', 'unknown')),
}
print(json.dumps(info, indent=2))
"

du -sh /path/to/model/
ls -lh /path/to/model/*.safetensors

Model Analysis:
  Model path:       <path or HuggingFace ID>
  Model type:       <model_type from config>
  Hidden layers:    <num_hidden_layers>
  Linear layers:    ~<estimated count>
  MoE:              Yes/No
  Exclude defaults: [lm_head]
  Risks:            <list or "None">
  Compatibility:    OK / <version constraints>

© amd, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills-impl/l1-atomic/torch/quark-torch-model-intake of amd/Quark.

Open the folder on GitHubat commit 313cb0b