All models › alibaba
qwen3-vl-235b-a22b-thinking
alibaba · Apache 2.0 license · on Arena since 30 Sept 2025
Lab chat Download
Arena score1401#152 of 416 in Chat, paid models included
Size235.7 B22 B active per token (mixture of experts)
4-bit download143 GBweights only, Q4_K_M
Max context256Ktokens, 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
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 | Does not fit | — |
| RTX 4060 Ti 16 GB | 16 GB | Does not fit | — |
| RTX 3090 | 24 GB | Does not fit | — |
| RTX 4090 | 24 GB | Does not fit | — |
| RTX 5090 | 32 GB | Does not fit | — |
| RX 7900 XTX | 24 GB | Does not fit | — |
| 2 × RTX 3090 | 48 GB | Does not fit | — |
| 4 × RTX 3090 | 96 GB | Does not fit | — |
| Mac M4 Max 128 GB | 96 GB | Does not fit | — |
| Ryzen AI Max+ 395 128 GB | 96 GB | Does not fit | — |
| 8 × H100 SXM | 640 GB | Fits in GPU | 99 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 | 128K context | Quality vs full |
|---|---|---|---|---|
| Q3_K_M | 120 GB | 125 GB | 144 GB | +4.7% noticeable loss |
| Q4_K_M | 145 GB | 150 GB | 169 GB | +1.2% very small loss |
| Q5_K_M | 170 GB | 174 GB | 193 GB | +0.4% near-lossless |
| Q6_K | 195 GB | 200 GB | 219 GB | +0.2% near-lossless |
| Q8_0 | 253 GB | 257 GB | 276 GB | ≈ 0% same as full |
| F16 | 474 GB | 478 GB | 497 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.
Chat score over time
1400145015001550
MayJunJulAugSeptOct
qwen3-vl-235b-a22b-thinking 1401Best paid model
Arena score from 17 Apr 2026 to 15 Oct 2026.
Vision score over time
1200125013001350
MayJunJulAugSeptOct
qwen3-vl-235b-a22b-thinking 1207Best paid model
Arena score from 10 Apr 2026 to 9 Oct 2026.