Feature Extraction
MLX
Safetensors
qwen3
apple-silicon
quantized
mixed-precision
axquant
axq
development
MXFP4
embedding
sentence-similarity
4-bit precision
Instructions to use AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4 --local-dir AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download runtime_audit.json from AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4: direct link, hf CLI and curl.
- Browser
- Download file 1.77 kB
-
https://huggingface.co/AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4/resolve/main/runtime_audit.json
- Command line
-
hf download hf://AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4/runtime_audit.json
-
curl -L -o runtime_audit.json https://huggingface.co/AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4/resolve/main/runtime_audit.json
1.77 kB
| { | |
| "applied_config_corrections": [], | |
| "current_config_sha256": "2f904fa350d2a8e42c85c6e4387722e9e415879b3b4b4b4a3a6e31141e832cb3", | |
| "date": "2026-10-06", | |
| "header_sha256": { | |
| "model.safetensors": "4aa68a81445248b72f945795162700c6fa857ae08fdd1af4e7cde5b6f43eaa20" | |
| }, | |
| "input_bindings": { | |
| "axquant_manifest.json": "4af8f2968a2b4f2a33ba1c0593d29981d71f171b51dec76efe9d36dd392d9a03", | |
| "config.json": "2f904fa350d2a8e42c85c6e4387722e9e415879b3b4b4b4a3a6e31141e832cb3", | |
| "model.safetensors.index.json": "2e57114e2df1fa97154323c49df2dc3710c777d52a32df76488485060ba92d57" | |
| }, | |
| "issues": [], | |
| "model_type": "qwen3", | |
| "mtp_files": [], | |
| "ngram_action": "none; do not invent n-gram data", | |
| "ngram_files": [], | |
| "ngram_quantization": [], | |
| "ngram_table_metadata": null, | |
| "ngram_tensor_count": 0, | |
| "quality_certified": false, | |
| "quantization": { | |
| "quantization": { | |
| "container_mode": "affine", | |
| "per_module_modes": { | |
| "affine": 1, | |
| "mxfp4": 252 | |
| }, | |
| "physical_recipe_issues": [] | |
| }, | |
| "quantization_config": { | |
| "container_mode": "affine", | |
| "per_module_modes": { | |
| "affine": 1, | |
| "mxfp4": 252 | |
| }, | |
| "physical_recipe_issues": [] | |
| } | |
| }, | |
| "removed_source_evidence": [], | |
| "repo_id": "AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4", | |
| "runtime_arch_id": null, | |
| "runtime_verified": false, | |
| "schema_version": "axquant.hub-runtime-audit.v1", | |
| "scope": "Pinned remote config/index/Safetensors header audit; no runtime load or generation claim.", | |
| "source_revision": "dc404d0335867fd0ce2c57047301ca5b5de5911c", | |
| "status": "no-audited-peer-export-profile", | |
| "unchanged_weight_sha256": { | |
| "model.safetensors": "e39949c394dde768e98dd49081bc2146787f0a16ff6c0bd67b9c24f673e2c36c" | |
| } | |
| } | |