Measured over the last 30 days
- Models Tracked
- 30
- Avg Tokens / Second
- 12.10
- Avg Time to First Token (ms)
- 15278.00
- Last Updated
- Oct 14, 2026
All venice models
30 live · one row per model · fastest first · 2 folded behind their current lane| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| Qwen3 Coder 480B A35B | 44.20 | 44.20 | 44.20 | 730.00 |
| Uncensored | 33.30 | 28.10 | 38.50 | 800.00 |
| Mistral Small 3.2 24B | 32.00 | 12.50 | 51.50 | 510.00 |
| Gemma 4 31B | 24.30 | 18.30 | 33.70 | 570.00 |
| GLM 5.2 | 23.90 | 16.30 | 31.60 | 2250.00 |
| Gemma 4 26B A4B | 22.60 | 3.60 | 37.60 | 1400.00 |
| GLM 5 | 18.30 | 18.30 | 18.30 | 1940.00 |
| Qwen3.8 2.4T A95B | 15.50 | 15.50 | 15.50 | 3110.00 |
| Kimi K2.7 Code | 15.10 | 6.24 | 30.20 | 4760.00 |
| Qwen3 235B A22B Instruct 2507 | 13.90 | 9.24 | 21.20 | 1840.00 |
| MiMo-V2.6-Flash | 13.40 | 13.40 | 13.40 | 2750.00 |
| MiniMax M3 | 13.10 | 4.31 | 19.60 | 5410.00 |
| Qwen3 VL 235B A22B Instruct | 11.80 | 7.77 | 15.80 | 2020.00 |
| Qwen3.5-35B-A3B | 9.12 | 9.12 | 9.12 | 6770.00 |
| DeepSeek V4 Pro 0423 | 8.76 | 2.19 | 22.70 | 11200.00 |
| MiMo-V2.5 | 7.99 | 0.91 | 15.10 | 32800.00 |
| DeepSeek V3.2 | 7.85 | 2.21 | 10.80 | 2620.00 |
| Qwen3.6 35B A3B | 7.64 | 6.16 | 11.20 | 8430.00 |
| Qwen3.5-9B | 6.96 | 6.96 | 6.96 | 8830.00 |
| DeepSeek V4 Flash 0731 | 6.44 | 2.14 | 10.70 | 16600.00 |
| DeepSeek V4 Flash 0423 | 5.75 | 4.26 | 8.74 | 10300.00 |
| Qwen3.5 397B A17B | 4.10 | 2.97 | 6.79 | 16200.00 |
| Kimi K2.5 | 3.85 | 3.85 | 3.85 | 15200.00 |
| gpt-oss-120b | 3.70 | 3.70 | 3.70 | 13700.00 |
| GLM 4.7 Flash | 1.81 | 1.81 | 1.81 | 23700.00 |
| Kimi K2.6 | 1.75 | 0.64 | 3.24 | 53800.00 |
| MiniMax M2.5 | 1.63 | 0.68 | 2.57 | 46900.00 |
| GLM 4.6 | 1.49 | 0.66 | 2.32 | 60000.00 |
| GLM 5.1 | 1.45 | 1.32 | 1.58 | 42900.00 |
| Qwen3 235B A22B Thinking 2507 | 1.26 | 0.72 | 1.80 | 60300.00 |
Frequently Asked Questions
Which venice model is fastest?
Based on recent tests, Qwen3 Coder 480B A35B shows the highest average throughput among tracked venice models.
How many recent measurements feed this dashboard?
This provider summary aggregates 3229 individual prompts measured across 2771 monitoring runs over the past month.