| ▲ | Qwen3-Next: Towards Ultimate Training and Inference Efficiency(qwen.ai) | |
| 15 points by bratao a day ago | 1 comments | ||
| ▲ | derac a day ago | parent [-] | |
This seems very promising, they are matching Qwen3-235B-A22B-Instruct-2507. It should run on 8-12GB vram with 64 gb ram decently well. | ||