Run Qwen3-Coder-30B on-premises
○ Memory-fit arithmetic — checkable math, not a benchmark
Qwen3-Coder-30B-A3B is a sparse mixture-of-experts model built for code — 30.5 billion total parameters with about 3 billion active per token, under the permissive Apache-2.0 license, with a native 256K-token context window (extendable further with YaRN). The small active budget makes it fast; the long context makes it useful across a whole repository, not just a single file.
It is a natural fit for a private coding agent: pointed at OpenCode on your machine, your source never leaves it. Here is the arithmetic against a machine with 128 GB of memory.
Memory fit in 128 GB
| Parameters | 30.5B total, ~3B active per token (128 experts, MoE) |
|---|---|
| 4-bit weights (the practical choice) | ~15–18 GB |
| 8-bit weights | ~31 GB |
| Reference memory | 128 GB (one machine) |
| Left for context cache + system at 4-bit | roughly 100+ GB — room for a repo-scale context |
| Native context | 256K tokens (extendable via YaRN) |
Weights are the small part here: at 4-bit the ~15–18 GB of parameters leave the overwhelming majority of 128 GB for the KV cache — which is exactly what a long, repository-scale context needs. The ~3B active budget also keeps it fast to serve.
What it serves well
- A private coding agent that reasons over a whole repository, running on your machine — pair it with OpenCode so source never leaves it.
- Agentic tool use and function calling for automated engineering workflows.
- Fine-tuning into a house coder on your own codebase via the LLM Factory, then delivered back onto your machine.
- Fast interactive assistance thanks to the ~3B active-parameter budget.
Honest limits
- Memory arithmetic, not a benchmark — and the model sits well inside 128 GB, with room to spare.
- A ~3B active budget is efficient, not the raw capability of a frontier dense model; for the hardest reasoning we would size a larger model and quantify the trade-off in the assessment.
- Very long contexts consume the KV-cache headroom that makes this model attractive — real throughput at 256K tokens is workload-dependent; we size it for your case.
Frequently asked questions
Does Qwen3-Coder-30B fit in 128 GB of memory?
Easily — ~15–18 GB of weights at 4-bit against 128 GB, leaving roughly 100 GB for the context cache. That headroom is the point: it is what lets the model hold a repository-scale context.
License?
Apache-2.0 — permissive and commercial-friendly, no separate agreement required.
How does this pair with OpenCode?
OpenCode runs on your machine and points at the local model, so your code is analysed and generated entirely on hardware you own.
Find out which model fits your work
An AI diagnostic maps your processes, classes what is sensitive and sizes the model and the hardware against your real tasks.