Qwen3-Coder-Next
Official · BF16 · safetensors
Runtime certified: Transformers vLLM SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Qwen · Code · Qwen3 Coder Next
Qwen3 Coder Next: Specs, GPU requirements, hosting & deployment
Qwen3 Coder Next is a current Coder release in the Qwen family, certified from its immutable official source revision.
Total parameters80.0B
Active parameters3.0B
Context window262,144 tokens
Release statusCurrent · Current
ArchitectureQwen3NextForCausalLM
ModalitiesText, Code
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2026-01-30
Architecture, strengths and use cases
Qwen3 Coder Next is an official self-hostable Qwen release in the Qwen Coder track. It uses Qwen3NextForCausalLM, carries 80B / 3B MoE, supports a verified context window of 262,144 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Qwen3 Coder Next uses Qwen3NextForCausalLM with 80B / 3B MoE. The stored architecture profile records 48 layers, hidden width 2048, 16 attention heads and a 262,144 token context ceiling where the official configuration publishes those fields.
Verified Qwen3NextForCausalLM architecture
262,144 token certified context
Official BF16, FP8, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Software engineering and code generation
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Qwen3-Coder-Next-FP8
Official · FP8 · safetensors
Runtime certified: Transformers vLLM SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| FP8 | safetensors | 8 | Official | Runtime certified |
Recommended hardware
Use only the listed transformers, vllm, sglang runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory153.48 GB
KV cache0.75 GB
Runtime overhead39.09 GB
Total with safety margin239.72 GB
Recommended best value
2× NVIDIA H200 SXM 141GB
282 GB total VRAM · nvswitch
42.28 GB headroom · Limited capacity
USD 4,690 / monthLowest-cost viable
5× NVIDIA L40S 48GB
240 GB total VRAM · pcie
0.28 GB headroom · Available
USD 2,530 / monthHighest performance
2× NVIDIA H200 SXM 141GB
282 GB total VRAM · nvswitch
42.28 GB headroom · Limited capacity
USD 4,690 / monthLicense and self-hosting considerations
The full 80B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Qwen3 Coder Next is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
千问3-Coder-Next, 千问3-Coder-Next-GGUF, 千问3-Coder-Next-FP8
Release timeline
qwen/qwen/qwen3-coder-next
Source details
Source revision: a7b14ccb2fe1311a2b86f746a4c9703a16ca8027f692c1ba7a61ebb94fce202a
Frequently asked questions
How much VRAM does Qwen3 Coder Next require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support Qwen3 Coder Next?
Certified upstream runtime evidence is available for transformers, vllm, sglang.
Can Qwen3 Coder Next be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26