What hardware do you need to run Qwen3-Coder 30B-A3B?

Qwen3-Coder 30B-A3B at Q4_K_M is 19 GB of weights, with a context ceiling of 256k tokens. Built for coding and agentic coding loops. The best local option at this size for Claude Code-style tooling. On the cheapest machine that runs it, a Framework Desktop, 32GB, it generates 27 tok/s at 32k of context, worked out from memory bandwidth.

How good is Qwen3-Coder 30B-A3B, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 10, which puts it in the Below every hosted tier band. Fine for simple, well-specified tasks. Noticeably less capable than anything the big labs sell today. See the whole table.

• Summarising — usable
• Translation — usable
• Everyday coding — good
• Reasoning & maths — usable
• Agentic work — usable

Head to head: vs Qwen3-Coder Next, the next model down the leaderboard. Also head to head: vs Qwen3 30B-A3B Instruct 2507, the last-generation Qwen nearest it in size. One more model needs much the same memory at 32k of context: vs Nemotron 3.5 Bolt 74B-A9B.

What Qwen3-Coder 30B-A3B costs either way

Renting the same model costs $0.07 per million input tokens and $0.28 per million output (OpenRouter, cheapest active endpoint, checked 2026-10-29). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill. What a million tokens costs each way puts the two prices side by side.

Machines that run Qwen3-Coder 30B-A3B

Every machine here runs it, but not to the same length. The Strix Halo Framework Desktop, 32GB stops at 32k; the DGX Spark GB10 Grace Blackwell, 128GB takes it to 256k, which is this model's own ceiling and the longest the calculator offers. The weights are the same size on every machine; what differs is the memory left for the key-value cache, which grows with every token you keep.

The table is the cheapest machine in each family, not the only one that runs it: 41 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every Mac Studio and Strix Halo box at any size, every NVIDIA card with 24GB or more, every Mac mini and MacBook Pro with 48GB or more, the Radeon AI PRO R9700, 32GB and the DGX Spark, 128GB. One table sets every machine against the others: price, the memory its GPU can use, what it holds and how long it takes to pay for itself.

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration. The longest context is the longest setting the calculator offers that the machine still holds this model at, cache included, and no machine is shown taking it past its own 256k limit. Each one opens the calculator on that machine at that length.

For scale, the calculator starts from 80 tok/s for a hosted API and times a local machine against it. 1 of the 7 above reaches it, and the slowest is 18 tok/s.

The cheapest machine that runs it is sold with 32 GB. There is a page on what 32 GB runs, machine by machine: it names the 6 machines here sold at that size, and the 32 current models the roomiest of them holds at 32k, this one among them.

It fits in less memory than that: the smallest size here that runs it at 32k is 24 GB, on the GeForce RTX 3090, 24GB at $1,499, card only, which hands a model 23 GB and is no longer sold.

Run Qwen3-Coder 30B-A3B at 256k on the DGX Spark GB10 Grace Blackwell, 128GB

How much memory does Qwen3-Coder 30B-A3B need at 256k?

Every figure above is priced at 32k of context. At 256k, which is this model's own ceiling and the longest the calculator offers, Qwen3-Coder 30B-A3B needs 44.3 GB rather than 21.8 GB. The weights are the same either way; the key-value cache goes from 3.2 GB to 25.8 GB.

28 of the 37 machines here still sold at a published price hold Qwen3-Coder 30B-A3B at 32k and 20 hold it at 256k. The cheapest still sold goes from the Framework Desktop, 32GB at $1,269 to the Corsair AI Workstation 300, 64GB at $1,700.

On the Corsair AI Workstation 300, 64GB it runs 27 tok/s estimated at 32k and 5.1 tok/s estimated at 256k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

What has been measured running Qwen3-Coder 30B-A3B

One of the speeds in the table above was measured, and there are more measurements than that table shows. Ten machines here have a published speed for Qwen3-Coder 30B-A3B. The table above has one of them; of the other nine, four are no longer sold and five are still sold but not the cheapest of their family. They are below, as published and again at 32k of context, which is what every other speed on this page is taken at.

A published figure is what its source reports, at the window the model was run at. The 32k figure is that measurement read at 32k of context: every token generated reads the weights and the whole key-value cache, so the longer the window the slower it runs. A discontinued machine's price is the one it launched at. Where two memory tiers of one machine carry the same figure, the speed is set by the bandwidth of the chip they share rather than by the amount of memory. Each published figure links the source that took it.

Two more machines, at a shorter window

The table above lists the machines that run it at 32k, the context the calculator starts on, where Qwen3-Coder 30B-A3B needs 22 GB. Two more machines hold it at a shorter window, because the weights are the same size either way and the key-value cache is not. None of them is cheaper than the table above, which starts at $1,269.

One machine per family, cheapest first, from the same list as the table above. Each window is the longest setting the calculator offers that the machine still holds this model at, and it opens the calculator on that machine at that length. What it needs there is the weights plus the key-value cache at that window, measured against the memory each machine's GPU can address, which that machine's own page gives.

The specifics

Parameters

30.5B, of which 3.3B are active per token

Quantisation

Q4_K_M

Weights on disk

19 GB

KV cache

3.2 GB at 32k context. How weights and cache add up.

Maximum context

256k tokens (up to 1M with YaRN)

Licence

Apache 2.0

Sources

unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF, Qwen/Qwen3-Coder-30B-A3B-Instruct