CoolFace
Modelpublic

deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
5likes142downloads
Model Card

This model was converted to MLX format and quantized from Qwen3.6-35B-A3B using oMLX.

What is "oQ"?

See "oQ: oMLX Universal Dynamic Quantization" for details.

Quantizations

Text-OnlyVision-LanguageText-Only FP16Vision-Language FP16
[MLX-oQ8][01][MLX-VL-oQ8][05][MLX-oQ8-FP16][09][MLX-VL-oQ8-FP16][13]
[MLX-oQ6][02][MLX-VL-oQ6][06][MLX-oQ6-FP16][10][MLX-VL-oQ6-FP16][14]
[MLX-oQ5][03][MLX-VL-oQ5][07][MLX-oQ5-FP16][11][MLX-VL-oQ5-FP16][15]
[MLX-oQ4][04][MLX-VL-oQ4][08][MLX-oQ4-FP16][12][MLX-VL-oQ4-FP16][16]

See "Evaluation of various MLX quantizations" for details:

Qwen3.6-35B-A3B KLD/RAM chart

What is "VL"?

"VL" is Vision-Language, meaning quantization preserves the original model's multimodality.

No "VL" means quantization is Text-Only.

What is "FP16"?

"FP16" is an M1/M2 Apple Silicon tweak that delivers a very noticeable prompt processing boost, because older M-series lack native BF16 hardware support. See "Metal FP32 Vs BF16 Vs FP16 benchmark" for details.

No "FP16" means quantization is better suited for M3+ Apple Silicon.

[01]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ8 [02]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ6 [03]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ5 [04]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ4 [05]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8 [06]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ6 [07]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ5 [08]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ4 [09]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16 [10]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ6-FP16 [11]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ5-FP16 [12]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-oQ4-FP16 [13]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16 [14]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ6-FP16 [15]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ5-FP16 [16]: https://huggingface.co/deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ4-FP16