Fast inference platform optimized for production AI workloads with 250+ models.
| Model |
|---|
qwen3-1p7b-fp8-draft-131072fireworks/qwen3-1p7b-fp8-draft-131072 |
qwen3-1p7b-fp8-draft-40960fireworks/qwen3-1p7b-fp8-draft-40960 |
qwen3-235b-a22b-instruct-2507OSSfireworks/qwen3-235b-a22b-instruct-2507 |
qwen3-235b-a22b-instruct-2507OSSfireworks/qwen3-235b-a22b-instruct |
qwen3-30b-a3b-instruct-2507OSSfireworks/qwen3-30b-a3b-instruct-2507 |
qwen3-30b-a3b-instruct-2507OSSfireworks/qwen3-30b-a3b-instruct |
qwen3-30b-a3b-thinking-2507OSSfireworks/qwen3-30b-a3b-thinking-2507 |
qwen3-30b-a3b-thinking-2507OSSfireworks/qwen3-30b-a3b-thinking |
qwen3-4b-instruct-2507fireworks/qwen3-4b-instruct-2507 |
qwen3-4b-instruct-2507fireworks/qwen3-4b-instruct |