Qwen3 Coder 30B A3B Instruct
Qwen · released Jul 31, 2025 · Qwen/Qwen3-Coder-30B-A3B-Instruct
- Type
- Open weightsApache License 2.0
- Params
- 30.5B
- Context
- 262K
3B active per word · about 197K words of context
Our take
Written Aug 3, 2026Qwen3 Coder is a text-only coding model from Alibaba with a permissive Apache licence. It uses a mixture-of-experts design with 3 billion active parameters per word, yet scores well on the SWE-bench Verified coding benchmark.
Pick this for budget coding inference where the cheapest hosts offer strong value, for local deployment with open weights and a permissive licence, or for long-context code tasks up to 262,144 tokens. Skip it if you need chat or general reasoning benchmarks to guide your choice, or if you want guaranteed fast throughput from the cheapest providers.
The case for it
- Strong and improving coding benchmark result: 60.4% on SWE-bench Verified in September 2025, up 8.8 points from August 2025.
- Very few active parameters for the score achieved: 3 billion active from 30.5 billion total.
- Apache 2.0 licence allows commercial use, modification and redistribution.
- Wide price range means a cheap entry point exists among the eight tracked offers.
The case against it
- No chat or general reasoning benchmarks in our data — only SWE-bench Verified scores are available.
- Premium providers charge a steep markup: the most expensive host costs several times more than the cheapest for both input and output.
- Throughput is unmeasured for the cheapest hosts, so speed there is undisclosed.
How good is it?
IntelligencePuzzles, maths, exam questions
Nobody we watch has scored Qwen3 Coder 30B A3B Instruct for this. We would take the rating from Arena Text (overall).
CodingWriting and fixing code on its own
Nobody we watch has scored Qwen3 Coder 30B A3B Instruct for this. We would take the rating from Arena Coding.
AgenticPlanning, calling tools, staying on task
Qwen3 Coder 30B A3B Instruct is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 21st of 39 with 60.4.
WritingWe do not rate this
Nobody we watch has scored this model for writing. Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage.
Every published score for this model1 scoreEvery figure we hold, from 1 board, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Borderline fit on an estimated size. It leaves 1.6 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Comfortable fit
GeForce RTX 5090 · 32 GB
Room to spare. 9.6 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 2.8 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 8 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.070 in / $0.27 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.070 / $0.27 | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.070 / $0.27 | 160K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8 | $0.070 / $0.27 | 160K | 38 tok/s | No | No | Confirmed |
| SiliconFlowfp8 | $0.070 / $0.28 | 262K | 24 tok/s | No | No | Confirmed |
| Amazon Bedrock | $0.15 / $0.60 | 0 | not measured | No | No | Confirmed |
| Alibaba Cloud | $0.29 / $1.46 | 262K | 48 tok/s | No | Yesunknown period | Unknown |
| Alibaba Cloudfp8 | $0.29 / $1.46 | 262K | 45 tok/s | No | Yesunknown period | Unknown |
| DigitalOcean Gradient | $0.45 / $1.70 | 262K | 53 tok/s | No | No | Confirmed |
Novita AI
Amazon Bedrock
DigitalOcean GradientAcross the 8 listings we hold: 6 say they do not train on prompts, 0 say they do and 2 do not say. 4 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Novita AI | |||
| Novita AIfp8 | ✓ | ✓ | ✓ |
| SiliconFlowfp8 | ✓ | ✓ | ✓ |
| Amazon Bedrock | ✓ | ✗ | ✗ |
| Alibaba Cloud | ✓ | ✓ | ✗ |
| Alibaba Cloudfp8 | ✓ | ✓ | ✗ |
| DigitalOcean Gradient | ✓ | ✓ | ✓ |
Tool calling: 7 of 8 listings say yes, 1 publishes no parameter list. JSON output: 6 of 8 listings say yes, 1 says no, 1 publishes no parameter list. Strict schema: 4 of 8 listings say yes, 3 say no, 1 publishes no parameter list.
Models people weigh against Qwen3 Coder 30B A3B Instruct
When we formed this view
Dates behind this page
Prices last checked 3d ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 1 of 8 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 8 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- Qwen/Qwen3-Coder-30B-A3B-Instruct
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- qwen-qwen3-coder-30b-a3b-instruct