Downloads · 30 days
21
2% of all-time downloads
QwQ-32B-exl2
bartowski/QwQ-32B-exl2
QwQ-32B-exl2 is a text generation model from bartowski. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.2.8"turboderp's ExLlamaV2 v0.2.8</a for quantization.
All-time downloads
873
Public
Repo size
131 GB
Likes
8
Public
Repo makeup
Click a slice to open those files.
.json3.6 MB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Mar 5, 2025
- Updated
- Mar 6, 2025
- SHA
- 64548735
Try a prompt
Base models
Model card
From the Hugging Face model README
Exllama v2 Quantizations of QwQ-32B
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.2.8">turboderp's ExLlamaV2 v0.2.8</a> for quantization.
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/Qwen/QwQ-32B
Prompt format
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>
Available sizes
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 34.9 GB | 37.6 GB | 41.6 GB | Max quality producable by ExLlamav2, generally unneeded but maximum performance |
| 6_5 | 6.5 | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, recommended. |
| 5_0 | 5.0 | 8.0 | 22.6 GB | 25.3 GB | 29.3 GB | Very high quality, usable at 4k context on 24GB. |
| 4_25 | 4.25 | 6.0 | 19.5 GB | 22.2 GB | 26.2 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| 3_5 | 3.5 | 6.0 | 16.5 GB | 19.2 GB | 23.2 GB | Lower quality, only use if you have to. |
| 3_0 | 3.0 | 6.0 | 14.3 GB | 17.0 GB | 21.0 GB | Very low quality, usable with 16gb of VRAM. |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/QwQ-32B-exl2 QwQ-32B-exl2-6_5
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:
Linux:
huggingface-cli download bartowski/QwQ-32B-exl2 --revision 6_5 --local-dir QwQ-32B-exl2-6_5
Windows (which apparently doesn't like _ in folders sometimes?):
huggingface-cli download bartowski/QwQ-32B-exl2 --revision 6_5 --local-dir QwQ-32B-exl2-6.5
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
- Task
- Text Generation
- License
- apache-2.0
- Languages
- en
- Created
- Mar 5, 2025
- Updated
- Mar 6, 2025