Will this model run on your hardware?
Can I run Qwen: Qwen3 Coder Next locally?
- 80B parameters (5.5B active, MoE)
- context up to 256K
- licence: apache-2.0
- Weights: Qwen/Qwen3-Coder-Next · GGUF: unsloth/Qwen3-Coder-Next-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 84.8 GB |
| Q6_K | 65.6 GB |
| Q5_K_M | 56.8 GB |
| Q4_K_M | 48.5 GB |
| MXFP4 | 48.0 GB |
| Q3_K_M | 38.3 GB |
| Q2_K | 29.2 GB |
Run it locally
ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q4_K_M
llama serve -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_M
LM Studio: open unsloth/Qwen3-Coder-Next-GGUF