Analyze Model
analyze_modelDerive model architecture facts—parameter count, quantization, layers, and KV heads—from a Hugging Face repo's config.json to assess MLX models.
Instructions
Derive architecture facts (params, quantization, layers, KV heads) from config.json.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| repo_id | Yes | HF repo id, e.g. 'mlx-community/...-4bit' |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| is_moe | No | ||
| repo_id | Yes | ||
| head_dim | No | ||
| confidence | No | medium | |
| model_type | No | ||
| num_layers | No | ||
| hidden_size | No | ||
| max_context | No | ||
| architecture | No | ||
| num_kv_heads | No | ||
| quantization | Yes | MLX quantization parameters (from config.json `quantization` block). | |
| sliding_window | No | Window (tokens) of sliding-window layers. | |
| total_params_b | No | Total params in billions. | |
| active_params_b | No | Params READ per decoded token in billions: active experts + attention + lm_head; excludes the input-embedding table (row lookup only). Drives the speed estimate. | |
| weights_file_gb | No | Actual size of the safetensors files in GiB (from the Hub); preferred for memory. | |
| num_linear_layers | No | Linear-attention layers (constant-size state, no growing KV cache). | |
| kv_cache_supported | No | False for architectures where the standard GQA KV formula does not apply. | |
| num_sliding_layers | No | Layers whose KV cache is capped at the window. | |
| num_attention_heads | No | ||
| full_attention_head_dim | No | Head dim of full-attention layers if it differs (Gemma 4 global layers). | |
| full_attention_kv_heads | No | KV heads of full-attention layers if they differ (Gemma 4 global layers). |