Models / Run locally
Run Qwen3 Coder Flash locally
Alibaba · 30B MoE (3B active) · open weights
Genuinely laptop-friendly: 4-bit fits in ≈20GB, and the 3B active parameters make it fast even on a 24GB GPU or an M-series Mac — the best local coding value in the catalog.
By quantization
Hardware requirements
| Quantization | ≈ File size | ≈ Memory needed | Runs on |
|---|---|---|---|
| Q4_K_M (4-bit) | 17 GB | 20 GB | 24GB GPUs (RTX 3090/4090) and 32GB M-series Macs |
| Q8_0 (8-bit) | 32 GB | 37 GB | 48GB workstation GPUs or 64GB Macs |
| FP16 (full) | 63 GB | 72 GB | Multi-GPU workstations or 128–192GB Mac Studios |
Sizes are computed from the ≈30B parameter count with standard GGUF math and ~15% runtime overhead — verify against the model card before buying hardware. As a mixture-of-experts model only ≈3B parameters are active per token, which helps speed — but the full weights still have to fit in memory.
Local setup
How to run it
The shortest path is Ollama — it downloads a sensible default quantization and serves an OpenAI-compatible endpoint on localhost:
ollama run qwen3-coder:30bFor serious throughput on server hardware, vLLM with tensor parallelism is the standard serving stack; llama.cpp and MLX (Apple silicon) win below that line.
The API route
Or skip the GPU entirely
The same model is one API call away at $0.3 / M input · $0.9 / M output — no download, no VRAM math, metered to the exact call. Free starter credits cover your first runs, and because the weights are open, nothing locks you in: start metered, move to your own hardware if sustained volume ever justifies it.
FAQ
Frequently asked questions
Can my GPU run Qwen3 Coder Flash?
Qwen3 Coder Flash is 30B MoE (3B active). At 4-bit quantization you need roughly 20GB of memory (24gb gpus (rtx 3090/4090) and 32gb m-series macs). Genuinely laptop-friendly: 4-bit fits in ≈20GB, and the 3B active parameters make it fast even on a 24GB GPU or an M-series Mac — the best local coding value in the catalog.
Is there a Qwen3 Coder Flash GGUF?
Open-weight releases in this family get community GGUF conversions on Hugging Face shortly after release — search the model name plus "GGUF" and pick the quantization your memory allows from the table above.
Is running Qwen3 Coder Flash locally cheaper than the API?
Only at sustained volume. The API price is $0.3 / M input · $0.9 / M output with no hardware, electricity, or ops cost — a machine that can serve this model costs more per month idle than most teams' entire inference bill. Prototype metered, self-host when utilization justifies it.
Can I use the outputs commercially?
Apache-2.0 open weights; commercial use permitted.
Explore
Run other models locally
One key. Every model. Exact prices.
Prototype on Qwen3 Coder Flash with free starter credits while the weights download. Free starter credits included — no subscription required.