Qwen/Qwen3-Coder-Next-FP8
no scores extracted for this variant.
| title | author | status | comments | type |
|---|---|---|---|---|
| TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture | vigneshwar234 | open | 0 | disc |
| Anyone running this on AMD MI300X / vLLM ROCm 7 at 256K context? | ZeroR3 | open | 0 | disc |
| Tested DGX Spark setup for Qwen3-Coder-Next-FP8 with Continue/Cline | ztolley | open | 0 | disc |
| Cannot deploy with vllm on p4de.24xlarge with vllmV1 using --tensor-parallelization 8 | HenryGuillaumet | open | 0 | disc |
| docs: update README.md | quocbao747 | open | 0 | disc |