Alibaba
Qwen3-Coder-Next (80B parameters) requires approximately 52.1 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 3B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 60 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Qwen3-Coder-Next on your machine.
Run
ollama run qwen3-coder-nextQuick specs
About this model
Related models
Inference speed
Estimated decode speed (tokens/sec) for Qwen3-Coder-Next at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~49 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 48.9 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 40.7 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 38.6 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 30.2 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 21.7 | Too big |
 RTX 5090 32GB | 32 GB | Q4_K_M | 20.8 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 16.6 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 15.3 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 10.8 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 7.8 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 7.0 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 6.6 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 6.2 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 3.8 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.4 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 31.2 GB | Low | — |
Q3_K_S | 3 | 39.2 GB | Low | — |
NVFP4 | 4 | 44.8 GB | Medium | — |
Q4_K_M | 4 | 48.8 GB | Medium | — |
Q5_K_M | 5 | 57.6 GB | High | — |
Q6_K | 6 | 65.6 GB | High | — |
Q8_0 | 8 | 85.6 GB | Very High | — |
F16 | 16 | 164.0 GB | Maximum | — |
Quality benchmarks
Coding
Reasoning
Source: official · 2026-01-30
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Qwen3-Coder-Next (80B parameters) requires approximately 52.1 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, MacBook Pro M3 Max 128GB can run Qwen3-Coder-Next with a compatibility score of 92/100. It provides 128 GB of memory and achieves approximately 23.2 tokens per second.
The recommended quantization for Qwen3-Coder-Next is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Qwen3-Coder-Next: NVIDIA A100 80GB (score: 97/100), NVIDIA H100 80GB (score: 97/100), NVIDIA A800 80GB (score: 97/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Qwen3-Coder-Next is well-suited for coding as well as reasoning, agentic. It was designed with these use cases in mind.
See also