Downloads · 30 days
9
2% of all-time downloads
Qwen3-VL-32B-Instruct-Heretic-FP8-DYNAMIC
genevera/Qwen3-VL-32B-Instruct-Heretic-FP8-DYNAMIC
Qwen3-VL-32B-Instruct-Heretic-FP8-DYNAMIC is a image-to-text model from genevera. Use it when you need a caption or text from an image.
This is an FP8 quant of coder3101/Qwen3-VL-32B-Instruct-Heretic.
All-time downloads
472
Public
Parameters
33.4B
35.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors35.5 GB · 100%
Parameter types
How the weights are stored.
F8_E4M331.2B · 94%
Base models
Model card
From the Hugging Face model README
Model Card for genevera/Qwen3-VL-32B-Instruct-Heretic-FP8-DYNAMIC
<!-- Provide a quick summary of what the model is/does. -->This is an FP8 quant of coder3101/Qwen3-VL-32B-Instruct-Heretic.
vllm (pretrained=genevera/Qwen3-VL-32B-Instruct-Heretic-FP8-DYNAMIC,add_bos_token=True,max_model_len=161184,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version| Filter |n-shot| Metric | |Value| |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.924|± |0.0168|
| | |strict-match | 5|exact_match|↑ |0.928|± |0.0164|
- Task
- Image-to-Text
- Type
- qwen3_vl
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025