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.

Cheapest machine that runs itStrix Halo Framework Desktop, 32GB at $1,269

Fastest of the ones listedMac Studio M5 Ultra, 96GB — 69 tok/s at 32k context

Honest answer on costPays back in 102 years at 500k tokens a day.

How good is it, 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. Score source. See the whole table.

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

What it costs either way

Renting the same model costs $0.07 per million input tokens and $0.27 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-03). 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.

Machines that run it

Machine	Price	Speed at 32k	Pay-back
Strix Halo Framework Desktop, 32GB	$1,269	27 tok/s estimated	Pays back in 102 years	Run the numbers
Mac mini M5 Pro, 48GB	$2,299	18 tok/s estimated	Pays back in 213 years	Run the numbers
Mac Studio M5 Max, 36GB	$2,499	26 tok/s estimated	Pays back in 206 years	Run the numbers
MacBook Pro M5 Pro (16-inch), 48GB	$3,599	18 tok/s estimated	Pays back in 334 years	Run the numbers
DGX Spark GB10 Grace Blackwell, 128GB	$4,699	34 tok/s measured	Pays back in 370 years	Run the numbers

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 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
Maximum context: 256k tokens (256k natively; up to 1M with YaRN)
Licence: Apache 2.0
Sources: source 1, source 2