Qwen2.5-VL-32B-Instruct-AWQ
In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning. This has also significantly improved the model's subjective user experience, with response styles adjusted to better align with human preferences. Particularly for objective queries such as mathematics, logical reasoning, and knowledge-based Q&A, the level of detail...
Params
33.5 B
Context
128,000
Downloads 30d
993 K
Likes
65
Download history
daily snapshots · 53 days
▲ 1.1 M in the last 30 days (52.3%)
2.2 M993 K
Aug 23Sep 2Sep 12Sep 21
2.2 M915 K
Jul 31Aug 17Sep 4Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | i32 | 20.7 GB | 28.3 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 125K ctx | 20.7 GB | 101.7 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen2_5_VLForConditionalGeneration
- Parameters
- 33.5 B
- Tensor type
- I32
- Context length
- 128,000
- Vocabulary
- 152,064
- Layers / heads
- 64 / 40
- Licence
- apache-2.0
- First seen on the Hub
- 2025-03-26
- Base model
- Qwen2.5-VL-32B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-31
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any image-text-to-text model