All models › alibaba
Arena score1152#117 of 165 in Vision, paid models included
Size33.5 Bparameters
4-bit download20 GBweights only, Q4_K_M
Max context125Ktokens, from the model config
Where to use it for free
- The lab's own chat: chat.qwen.ai (free with daily limits)
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
| Arena | Score | Rank | Votes |
|---|---|---|---|
| Vision | 1152 | #117 of 165 | 1K |
Rank among all models, paid ones included. Source: Arena leaderboard dataset.
Speed on popular hardware
| Hardware | GPU memory | Fits? | Speed |
|---|---|---|---|
| RTX 3060 12 GB | 12 GB | GPU + 64 GB RAM | 3.7 tok/s |
| RTX 4060 Ti 16 GB | 16 GB | GPU + 64 GB RAM | 4.0 tok/s |
| RTX 3090 | 24 GB | GPU + 64 GB RAM | 9.3 tok/s |
| RTX 4090 | 24 GB | GPU + 64 GB RAM | 9.6 tok/s |
| RTX 5090 | 32 GB | Fits in GPU | 43 tok/s |
| RX 7900 XTX | 24 GB | GPU + 64 GB RAM | 9.4 tok/s |
| 2 × RTX 3090 | 48 GB | Fits in GPU | 22 tok/s |
| 4 × RTX 3090 | 96 GB | Fits in GPU | 21 tok/s |
| Mac M4 Max 128 GB | 96 GB | Fits in GPU | 13 tok/s |
| Ryzen AI Max+ 395 128 GB | 96 GB | Fits in GPU | 6.2 tok/s |
| 8 × H100 SXM | 640 GB | Fits in GPU | 67 tok/s |
Estimate at 4-bit with 32K context, 64 GB of DDR5 for offload. Speed ≈ memory bandwidth × 70% ÷ data read per token; real numbers vary by about ±30%.
GPU memory needed
| Level | 8K context | 32K context | Quality vs full |
|---|---|---|---|
| Q3_K_M | 19 GB | 26 GB | +6.7% noticeable loss |
| Q4_K_M | 23 GB | 29 GB | +1.8% small loss |
| Q5_K_M | 27 GB | 33 GB | +0.6% near-lossless |
| Q6_K | 30 GB | 37 GB | +0.2% near-lossless |
| Q8_0 | 38 GB | 45 GB | ≈ 0% same as full |
| F16 | 70 GB | 76 GB | ≈ 0% same as full |
Weights + context cache (from the model's architecture) + runtime. Quality: increase in perplexity against the full model, from llama.cpp tests, scaled by model size. Simulate your own setup.
Vision score over time
12001300
MayJunJulAugSeptOct
qwen2.5-vl-32b-instruct 1152Best paid model
Arena score from 10 Apr 2026 to 9 Oct 2026.
Similar free models in Vision
- glm-4.5v 1154 · 107.7 B
- mistral-small-2506 1142
- llama-4-maverick-17b-128e-instruct 1142 · 401.6 B
- glm-4.6v 1164 · 107.7 B
- gemma-3-27b-it 1164 · 27.4 B
- mistral-small-3.1-24b-instruct-2503 1136