Alibaba
Qwen3-Coder-Next
Qwen Coder family, 80B parameters, recommended as Q4_K_M for first-pass local usage in V1.
Params
80B
Context
256K
License
Apache 2.0
Best runtime
Ollama
Recommended hardware
First-pass fit across priority GPUs
| Hardware | Fit | Decode | Safe ctx |
|---|---|---|---|
| NVIDIA A10 24GB | Too heavy | 16.7 tok/s | 8K |
| NVIDIA A100 40GB | Too heavy | 43.2 tok/s | 12K |
| NVIDIA A100 80GB | Runs well | 78.6 tok/s | 23K |
| NVIDIA A16 64GB | Tight fit | 16.7 tok/s | 19K |