🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN ON CONSUMER GPU
Run Hy-MT2 30B-A3B on Consumer GPU hardware
15 options ranked by estimated speed at Q4 / 8k context.
| Hardware | Est tok/s | Fits 8k? | Max ctx | ~Price |
|---|---|---|---|---|
| Instinct MI430X → | ~1,067.9 | yes | 1446k | — |
| AMD Instinct MI455X → | ~898.3 | yes | 1446k | — |
| Instinct MI455X → | ~898.3 | yes | 1446k | — |
| Instinct MI440X → | ~898.3 | yes | 1446k | — |
| Huawei Ascend 950DT → | ~188.1 | yes | 436k | — |
| NVIDIA GeForce RTX 5090 → | ~92.8 | yes | 42k | ~$1,999 |
| FuriosaAI RNGD → | ~70.5 | yes | 99k | — |
| NVIDIA GeForce RTX 4090 → | ~52.2 | yes | 14k | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | ~52.2 | yes | 14k | ~$1,999 |
| NVIDIA GeForce RTX 3090 → | ~48.5 | yes | 14k | ~$1,499 |
| AMD Radeon RX 7900 XTX → | ~44 | yes | 14k | ~$999 |
| Intel Arc Pro B70 → | ~26.1 | yes | 42k | — |
| Intel Arc Pro B60 → | ~19.5 | yes | 14k | — |
| NVIDIA DGX Spark → | ~14.1 | yes | 370k | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | ~11.7 | yes | 370k | ~$1,999 |
Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.
FAQ
What Consumer GPU hardware runs Hy-MT2 30B-A3B?▶
On GenAIList, 15 Consumer GPU options can run Hy-MT2 30B-A3B at Q4 — the fastest is the Instinct MI430X at ~1,067.9 tok/s.
How fast is Hy-MT2 30B-A3B on Consumer GPU hardware?▶
Estimated generation speed ranges from ~11.7 to ~1,067.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.