Hugging Face's logo

blockblockblock
/
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-exl3-4.0bpw

Text Generation
Safetensors
exllamav3
qwen3_5_moe
exl3
quantized
mixture-of-experts
qwen
conversational
4-bit precision
Model card Files
xet
 Community
1
blockblockblock commited on
Commit
e777544
·
verified ·
1 Parent(s): ab370d7

docs: proper model card with base-model link + inference notes

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -45,7 +45,7 @@ bits_per_weight: 4.0
45
 
46
  | BPW   |   Head bits   |   Calibration rows   |   Size   |   Status |
47
  | :---: | :---: | :---: | ---: | :--- |
48
- | 3.0 | 8 | 128 | <i>~15&nbsp;GB</i> | <sub>queued</sub> |
49
  | **4.0** | 8 | 128 | **19.5&nbsp;GB** | <kbd>this repo</kbd> |
50
  | 4.5 | 8 | 250 | 21.6&nbsp;GB | [link](https://huggingface.co/blockblockblock/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-exl3-4.5bpw) |
51
  | 5.0 | 8 | 250 | 23.7&nbsp;GB | [link](https://huggingface.co/blockblockblock/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-exl3-5.0bpw) |
 
45
 
46
  | BPW &nbsp; | &nbsp; Head bits &nbsp; | &nbsp; Calibration rows &nbsp; | &nbsp; Size &nbsp; | &nbsp; Status |
47
  | :---: | :---: | :---: | ---: | :--- |
48
+ | 3.0 | 8 | 128 | 15.3&nbsp;GB | [link](https://huggingface.co/blockblockblock/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-exl3-3.0bpw) |
49
  | **4.0** | 8 | 128 | **19.5&nbsp;GB** | <kbd>this repo</kbd> |
50
  | 4.5 | 8 | 250 | 21.6&nbsp;GB | [link](https://huggingface.co/blockblockblock/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-exl3-4.5bpw) |
51
  | 5.0 | 8 | 250 | 23.7&nbsp;GB | [link](https://huggingface.co/blockblockblock/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-exl3-5.0bpw) |