matt-here's picture
Upload 16 files
92023e0 verified
|
raw
history blame
2.21 kB
metadata
language:
  - en
  - zh
  - ko
license: apache-2.0
base_model: Jackrong/Qwopus3.5-27B-v3
tags:
  - unsloth
  - qwen
  - qwen3.5
  - reasoning
  - chain-of-thought
  - lora
  - competitive-programming
  - mlx
pipeline_tag: image-text-to-text
library_name: mlx

MLX-Qwopus3.5-27B-v3-vision-6bit

A 6-bit MLX quantization of Jackrong/Qwopus3.5-27B-v3 with some tweaks to bring back the multimodal capabilities.


Quantization Details

Property Value
Method 6-bit (6.661 bits per weight)
Tool mlx-vlm 0.4.2 via mlx-vlm.convert
Size ~22.9GB

Other Available Quants

Model Size Quantization Bits per weight Multimodal
Jackrong/MLX-Qwopus3.5-27B-v3-4bit 15.15 GB 4-bit 4.501 ✗
matt-here/MLX-Qwopus3.5-27B-v3-vision-4bit 16.08 GB 4-bit 4.695 ✓ (Vision)
matt-here/MLX-Qwopus3.5-27B-v3-5bit 18.56 GB 5-bit 5.501 ✗
matt-here/MLX-Qwopus3.5-27B-v3-vision-5bit 19.46 GB 5-bit 5.678 ✓ (Vision)
Jackrong/MLX-Qwopus3.5-27B-v3-6bit 21.88 GB 6-bit 6.501 ✗
(This model) 22.85 GB 6-bit 6.661 ✓ (Vision)
Jackrong/MLX-Qwopus3.5-27B-v3-bf16 53.81 GB bf16 16 ✗

GGUF quants - Jackrong/Qwopus3.5-27B-v3-GGUF


Credits