HyperAI
Command Palette
Search for a command to run...
What can this GPU run?
Choose a GPU setup and a capability to find the best open models that fit, and deploy one as an API.
| # | (0–10) | |||
|---|---|---|---|---|
| 1 | Qwen3-Coder-Next 2026.03 | NVFP4 | 164K | 9.30 |
| 2 | Qwen3.8-27B 2026.08 | FP8 | 248K | 9.25 |
| 3 | Qwen3.5-35B-A3B 2026.02 | FP8 | 256K | 9.13 |
| 4 | Qwen3.5-27B 2026.02 |
| FP8 |
| 254K |
| 9.13 |
| 5 | Qwen3.6-27B 2026.04 | FP8 | 248K | 9.02 |
| 6 | Qwen3.5-9B 2026.03 | FP16 | 256K | 8.27 |
| 7 | GLM-4.7-Flash 2026.01 | FP8 | 198K | 8.23 |
| 8 | Qwen3.6-35B-A3B 2026.04 | FP8 | 256K | 7.97 |
| 9 | Ministral-3-8B-Reasoning-2512 2026.07 | FP16 | 256K | 7.80 |
| 10 | gpt-oss-20b 2025.08 | FP16 | 128K | 7.80 |
| 11 | Qwen-AgentWorld-35B-A3B 2026.06 | FP8 | 91K | 7.30 |
| 12 | UI-Mate-democua-27B 2026.08 | FP8 | 251K | 6.80 |
| 13 | GLM-4.1V-9B-Thinking 2026.07 | FP16 | 64K | 6.80 |
| 14 | TaskMem 2026.06 | FP8 | 105K | 6.80 |
| 15 | gpt-oss-safeguard-20b 2026.01 | FP16 | 118K | 6.80 |
| 16 | Baichuan-M2-32B 2025.12 | FP8 | 98K | 6.80 |
| 17 | Gemma 4 12B 2026.06 | FP16 | 256K | 6.69 |
| 18 | Gemma 4 26B-A4B 2026.03 | FP16 | 166K | 6.69 |
| 19 | Gemma 4 31B 2026.03 | FP8 | 106K | 6.69 |
| 20 | UI-Mate-27B 2026.08 | FP8 | 251K | 6.30 |