Downloads · 30 days
85
28% of all-time downloads
mlx-community/Qwen3.5-122B-A10B-heretic-v2-2.34bit-msq
Qwen3.5-122B-A10B-heretic-v2-2.34bit-msq is a image-text-to-text model from mlx-community. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Mixed-precision MLX quantization of coder3101/Qwen3.5-122B-A10B-heretic-v2, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-lay…
Downloads · 30 days
85
28% of all-time downloads
All-time downloads
303
Public
Parameters
123B
43.3 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors43.3 GB · 100%
How the weights are stored.
U328.8B · 69%
From the Hugging Face model README
Mixed-precision MLX quantization of coder3101/Qwen3.5-122B-A10B-heretic-v2, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.
| Benchmark | Score | Samples |
|---|---|---|
| MMLU | 82.1% | 285 |
| HellaSwag | 92% | 200 |
| GSM8K | 90% | 200 |