Qwen · 9B to 32B · Mixture of experts

Qwen3 30B A3B

30.53 billion parameters in total, but only 3.34 billion are read for each token. That split is the whole point of the design: it costs the memory of a large model and the speed of a small one. Grouped-query attention keeps the cache small, so long contexts cost less here than on models of the same size.

General chatReasoning
Parameters30.53B
Active per token3.34B
Layers48
KV heads4 / 32
Native context40k
Vocabulary152k

Memory needed, by quantisation

At an 8k context window. Quality is our rough ranking of how much the compression costs you: anything at or above Q5 is hard to tell apart from the original in normal use.

Quantisation File size KV cache Total VRAM Quality What it costs you
Q8_0 30.21 GB 0.75 GB 31.69 GB 99% Lossless in practice. Use it when the memory is there.
Q6_K 23.32 GB 0.75 GB 24.79 GB 98% Very close to Q8 for two thirds of the size.
Q5_K_M 20.22 GB 0.75 GB 21.7 GB 96% The quality-first choice when Q6 will not fit.
Q4_K_M 17.17 GB 0.75 GB 18.64 GB 93% The default. Best size-to-quality ratio for local use.
IQ4_XS 15.11 GB 0.75 GB 16.58 GB 91% Importance-matrix 4-bit. Q4_K_S quality, smaller file.
Q3_K_M 13.9 GB 0.75 GB 15.37 GB 86% Degradation starts to show. A way to fit one size up.
IQ3_XXS 10.88 GB 0.75 GB 12.35 GB 79% Aggressive. Only worth it on very large models.

What a longer conversation costs

Same model at Q4_K_M, only the context window changes. The cache grows in a straight line with every token in the window.

ContextKV cacheTotal VRAMFits in 8 GBFits in 12 GBFits in 24 GB
4k 0.38 GB 18.21 GB no no yes
8k 0.75 GB 18.64 GB no no yes
16k 1.5 GB 19.52 GB no no yes
32k 3 GB 21.27 GB no no yes

The "fits" columns allow for the roughly 0.8 GB Windows keeps for the desktop.

Which hardware runs Qwen3 30B A3B

56 of 118 consumer devices run it at a quantisation worth using, at an 8k context window. Another 44 can load it only by compressing the weights far enough to damage the model, marked with a warning below.

DeviceMemoryVerdictQuantisationUsedSpeed
RTX PRO 6000 Blackwell
NVIDIA
96 GB Runs great Q8_0 31.69 GB 362.4 t/s
RTX 6000 Ada Generation
NVIDIA
48 GB Runs great Q8_0 31.69 GB 194.1 t/s
Apple M3 Ultra 96GB
Apple
96 GB Runs great Q8_0 31.39 GB 157.5 t/s
Apple M3 Ultra 256GB
Apple
256 GB Runs great Q8_0 31.39 GB 157.5 t/s
Apple M3 Ultra 512GB
Apple
512 GB Runs great Q8_0 31.39 GB 157.5 t/s
RTX A6000
NVIDIA
48 GB Runs great Q8_0 31.69 GB 155.3 t/s
Apple M1 Ultra 64GB
Apple
64 GB Runs great Q8_0 31.39 GB 153.9 t/s
Apple M1 Ultra 128GB
Apple
128 GB Runs great Q8_0 31.39 GB 153.9 t/s
Apple M2 Ultra 64GB
Apple
64 GB Runs great Q8_0 31.39 GB 153.9 t/s
Apple M2 Ultra 128GB
Apple
128 GB Runs great Q8_0 31.39 GB 153.9 t/s
Apple M2 Ultra 192GB
Apple
192 GB Runs great Q8_0 31.39 GB 153.9 t/s
Radeon PRO W7900
AMD
48 GB Runs great Q8_0 31.69 GB 153.4 t/s
Apple M4 Max 48GB
Apple
48 GB Runs great Q8_0 31.39 GB 105 t/s
Apple M4 Max 64GB
Apple
64 GB Runs great Q8_0 31.39 GB 105 t/s
Apple M4 Max 128GB
Apple
128 GB Runs great Q8_0 31.39 GB 105 t/s
Apple M1 Max 64GB
Apple
64 GB Runs great Q8_0 31.39 GB 76.9 t/s
Apple M2 Max 64GB
Apple
64 GB Runs great Q8_0 31.39 GB 76.9 t/s
Apple M2 Max 96GB
Apple
96 GB Runs great Q8_0 31.39 GB 76.9 t/s
Apple M3 Max 48GB
Apple
48 GB Runs great Q8_0 31.39 GB 76.9 t/s
Apple M3 Max 64GB
Apple
64 GB Runs great Q8_0 31.39 GB 76.9 t/s
Apple M3 Max 96GB
Apple
96 GB Runs great Q8_0 31.39 GB 76.9 t/s
Apple M3 Max 128GB
Apple
128 GB Runs great Q8_0 31.39 GB 76.9 t/s
NVIDIA DGX Spark 128GB
NVIDIA
128 GB Runs great Q8_0 31.69 GB 55.2 t/s
Apple M4 Pro 48GB
Apple
48 GB Runs great Q8_0 31.39 GB 52.5 t/s
Apple M4 Pro 64GB
Apple
64 GB Runs great Q8_0 31.39 GB 52.5 t/s
Jetson AGX Orin 64GB
NVIDIA
64 GB Runs great Q8_0 31.69 GB 41.4 t/s
Ryzen AI Max+ 395 64GB
AMD
64 GB Runs great Q8_0 31.69 GB 41 t/s
Ryzen AI Max+ 395 96GB
AMD
96 GB Runs great Q8_0 31.69 GB 41 t/s
Ryzen AI Max+ 395 128GB
AMD
128 GB Runs great Q8_0 31.69 GB 41 t/s
GeForce RTX 5090
NVIDIA
32 GB Runs great Q6_K 24.79 GB 445.2 t/s
Apple M4 Max 36GB
Apple
36 GB Just fits Q6_K 24.49 GB 129 t/s
Apple M3 Max 36GB
Apple
36 GB Just fits Q6_K 24.49 GB 94.5 t/s
Apple M3 Pro 36GB
Apple
36 GB Just fits Q6_K 24.49 GB 35.4 t/s
GeForce RTX 4090
NVIDIA
24 GB Runs great Q5_K_M 21.7 GB 279 t/s
GeForce RTX 3090 Ti
NVIDIA
24 GB Runs great Q5_K_M 21.7 GB 279 t/s
GeForce RTX 3090
NVIDIA
24 GB Runs great Q5_K_M 21.7 GB 259.1 t/s
GeForce RTX 5090 Laptop
NVIDIA
24 GB Runs great Q5_K_M 21.7 GB 248 t/s
Radeon RX 7900 XTX
AMD
24 GB Runs great Q5_K_M 21.7 GB 233.3 t/s
RTX A5000
NVIDIA
24 GB Runs great Q5_K_M 21.7 GB 212.6 t/s
Apple M1 Max 32GB
Apple
32 GB Runs great Q5_K_M 21.4 GB 105.3 t/s
Apple M2 Max 32GB
Apple
32 GB Runs great Q5_K_M 21.4 GB 105.3 t/s
Jetson AGX Orin 32GB
NVIDIA
32 GB Just fits Q5_K_M 21.7 GB 56.7 t/s
Ryzen AI Max+ 395 32GB
AMD
32 GB Just fits Q5_K_M 21.7 GB 56.2 t/s
Apple M1 Pro 32GB
Apple
32 GB Runs great Q5_K_M 21.4 GB 52.7 t/s
Apple M2 Pro 32GB
Apple
32 GB Runs great Q5_K_M 21.4 GB 52.7 t/s
Apple M5 32GB
Apple
32 GB Runs great Q5_K_M 21.4 GB 40.3 t/s
Apple M4 32GB
Apple
32 GB Runs great Q5_K_M 21.4 GB 31.6 t/s
Intel Core Ultra 9 288V 32GB
Intel
32 GB Just fits Q5_K_M 21.7 GB 29.8 t/s
Ryzen AI 9 HX 370 32GB
AMD
32 GB Just fits Q5_K_M 21.7 GB 28.1 t/s
Radeon RX 7900 XT
AMD
20 GB Just fits Q4_K_M 18.64 GB 219.2 t/s
Apple M4 Pro 24GB
Apple
24 GB Just fits IQ4_XS 16.28 GB 88.6 t/s
Apple M5 24GB
Apple
24 GB Just fits IQ4_XS 16.28 GB 49.7 t/s
Apple M4 24GB
Apple
24 GB Just fits IQ4_XS 16.28 GB 39 t/s
Ryzen AI 9 HX 370 24GB
AMD
24 GB Just fits IQ4_XS 16.58 GB 34.6 t/s
Apple M2 24GB
Apple
24 GB Just fits IQ4_XS 16.28 GB 32.5 t/s
Apple M3 24GB
Apple
24 GB Just fits IQ4_XS 16.28 GB 32.5 t/s
GeForce RTX 5080
NVIDIA
16 GB Runs great IQ3_XXS ! 12.35 GB 405.8 t/s
GeForce RTX 5070 Ti
NVIDIA
16 GB Runs great IQ3_XXS ! 12.35 GB 378.8 t/s
GeForce RTX 5080 Laptop
NVIDIA
16 GB Runs great IQ3_XXS ! 12.35 GB 324.7 t/s
GeForce RTX 4080 SUPER
NVIDIA
16 GB Runs great IQ3_XXS ! 12.35 GB 311.1 t/s

What to buy to run Qwen3 30B A3B

The cheapest hardware that runs it at a quantisation worth using and a speed you would not resent, at an 8k context window.

DevicePriceMemoryRuns it atSpeed
Radeon RX 7900 XT
AMD
$650 20 GB Q4_K_M 219.2 t/s Check price
GeForce RTX 3090
NVIDIA
$700 used 24 GB Q5_K_M 259.1 t/s Check price
GeForce RTX 3090 Ti
NVIDIA
$800 used 24 GB Q5_K_M 279 t/s Check price
Apple M4 32GB
Apple · whole machine
$999 32 GB Q5_K_M 31.6 t/s Check price
Ryzen AI Max+ 395 64GB
AMD · whole machine
$1,699 64 GB Q8_0 41 t/s Check price
Ryzen AI Max+ 395 96GB
AMD · whole machine
$1,999 96 GB Q8_0 41 t/s Check price
Ryzen AI Max+ 395 128GB
AMD · whole machine
$2,199 128 GB Q8_0 41 t/s Check price
GeForce RTX 5090
NVIDIA
$2,200 32 GB Q6_K 445.2 t/s Check price

Indicative prices reviewed 2026-09-01; used prices are marketplace typical. Options that cost more than a cheaper one with no more memory and no more speed are hidden. Price links are Amazon affiliate links. Change the standard, the context window or the budget in the buying tool.

These numbers also cover

Fine-tunes share their base model's architecture, so they need exactly the same memory. If you are looking for one of these, the figures above apply unchanged.

  • Qwen/Qwen3-Coder-30B-A3B-Instruct
  • Qwen/Qwen3-30B-A3B-Instruct-2507
  • mlabonne/Qwen3-30B-A3B-abliterated
  • Qwen/Qwen3-30B-A3B-Base
  • bineric/lynx-instruct-30b

Where it sits in the catalogue

Source: Qwen/Qwen3-30B-A3B on Hugging Face. Downloaded 2.4M times in the last month. Published 2025-04-27. Architecture figures are read from the repository's own configuration file, so they move when the model does.