Qwen3-Coder-Next
Q4 GGUF download: Qwen/Qwen3-Coder-Next-GGUF - 15.52 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
9.2
AA Index
Coding
36.2
AA Index
Agentic
0.9
AA Index
Intelligence Index - Qwen3-Coder-Next vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Agentic Index comparison
Benchmark data from Artificial Analysis · updated 2026-10-19.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.31 |
| Output (per 1M tokens) | $1.00 |
| Median speed (hosted API) | 97 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-10-19. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA Diamond | 73.7 |
| SWEBENCH | 70.6 |
| HLE | 10.1 |
| SciCode | 36.2 |
| IFBench | 35.2 |
| Terminal-Bench | 18.2 |
Source: Artificial Analysis component evals - updated 2026-10-19. Additional scores from Hugging Face OpenEvals official leaderboards - updated 2026-10-19.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve Qwen/Qwen3-Coder-NextNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Qwen3-Coder-Next
Qwen3-Coder-Next is a 79.7B-parameter apache-2.0 model from Qwen. It scores 9.2 on the Artificial Analysis Intelligence Index (coding 22.9). At Q4_K_M it needs roughly 46 GB of VRAM, placing it in the 24-48gb hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 79.7B |
| Context length | 262K tokens |
| License | apache-2.0 |
| Modalities | text |
| Released | 2026-01-30 |
| Weights | Qwen/Qwen3-Coder-Next |
Benchmarks
Artificial Analysis Intelligence Index - Qwen3-Coder-Next vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Qwen3-Coder-Next | 28.3 | 22.9 | 73.7 |
| GPT-5.5 (xhigh) | 60.2 | 59.1 | 93.5 |
| Claude Opus 4.8 (max) | 61.4 | 56.7 | 92 |
| Gemini 3.1 Pro Preview | 57.2 | 55.5 | 94.1 |
| Grok 4.3 (high) | 53.2 | 41 | 90.1 |
Source: Artificial Analysis (2026-06-04).
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~46 GB | RTX 6000 Ada, dual RTX 3090 |
| Q5_K_M | ~57 GB | A100 80GB, H100 |
| Q8_0 | ~85 GB | multi-GPU / datacenter |
| FP16 | ~159 GB | multi-GPU / datacenter |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve Qwen/Qwen3-Coder-NextPopularity
Qwen3-Coder-Next has 930,533 downloads in the last month on HuggingFace and 1,421 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Qwen3-Coder-Next need?
Qwen3-Coder-Next with 79.7B parameters needs approximately 46 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Qwen3-Coder-Next better than other Qwen models?
Qwen3-Coder-Next has 79.7B parameters with 262,144 context - a strong choice for general use.
What license is Qwen3-Coder-Next under?
Qwen3-Coder-Next is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Qwen3-Coder-Next well?
With 79.7B parameters, Qwen3-Coder-Next requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Qwen3-Coder-Next?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~57 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Qwen3-Coder-Next's context window handle?
Qwen3-Coder-Next supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Qwen3-Coder-Next?
Qwen3-Coder-Next competes with other 40B–120B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec