Run Qwen 3 30B-A3B on M5 Ultra

Qwen 3 30B-A3B runs at 162 tok/s (162.2 as recorded) on a 256 GB M5 Ultra, a community run reported by bohemiansilicon.com (MLX, 4-bit, 512-token random prompt, 128 generated, mean of 3). It needs about 18 GB of unified memory. It is Alibaba's 30B mixture-of-experts model (3B active), released under the Apache 2.0 licence.

Speed
community162
tok/s
First Token
—
seconds
RAM Needed
18
GB minimum
Engine
MLX
of this figure
Want to run Qwen 3 30B-A3B faster — or step up to bigger models? Find your Mac →

The figure

This is a community run: a real run, reported by its source and linked below. The index records it as given and never adjusts it.

MetricValue
Tokens per secondcommunity162 tok/s
Provenancecommunity run · bohemiansilicon.com
Quantization4-bit
EngineMLX
Prompt processing (prefill)community7602 tok/s at 8K context
Context512-token random prompt, 128 generated, mean of 3
Figure dated2026-11-11
Minimum RAM18 GB
Parameters30B MoE (3B active)
Chip bandwidth1228 GB/s

Every figure for Qwen 3 30B-A3B on the M5 Ultra

Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (18 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.

SpeedQuantEngineMac RAMContextSourceNote
sourced172 tok/s4-bitllama.cpp256 GBempty context, 128 generatedvsesmart.czVse Smart review: Mac Studio M5 Ultra (80-core GPU, 256 GB), macOS 27.0.1, measured 24 Oct; llama.cpp with every layer on the GPU, build not stated. 4-bit; the review does not name the GGUF type.
community162.2 tok/s4-bitMLX256 GB512-token random prompt, 128 generated, mean of 3bohemiansilicon.comBohemian Silicon, Mac Studio M5 Ultra (80-core GPU, 256 GB), macOS 27.2.1; mlx_lm.benchmark, mlx-lm 0.32.2 (MLX 0.32.4), mlx-community 4-bit. 138.0 tok/s with an 8K prompt. The post's second M5 Ultra unit measured within 0.35%. Published by Bohemian Silicon, which rents out this Mac.
sourced159 tok/s4-bitMLX256 GBempty context, 128 generatedvsesmart.czVse Smart review: Mac Studio M5 Ultra (80-core GPU, 256 GB), macOS 27.0.1, measured 24 Oct; MLX 0.32 with mlx-lm, point version not stated. 4-bit MLX; the review does not name the repo.
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Speed by context depth: Qwen 3 30B-A3B on the M5 Ultra

Measured figures only, each from its source’s own session; the index does not estimate long-context or prefill speed, so a missing cell is —. Each @ column is plain decode with that many tokens already in the prompt, from the same session as the row’s short-context figure: decode slows as the KV cache it reads grows. Prefill is prompt processing, the tokens per second a runtime reads a prompt at; with long agent contexts it sets how long you wait before the first token.

RunDecode (row)@8K@16KPrefill
llama.cpp · 4-bit · 256 GB Mac · vsesmart.czsourced172 tok/s
empty context, 128 generated
——sourced4535 tok/s
at 4K
MLX · 4-bit · 256 GB Mac · bohemiansilicon.comcommunity162.2 tok/s
512-token random prompt, 128 generated, mean of 3
community138 tok/s—community7602 tok/s
at 8K
MLX · 4-bit · 256 GB Mac · vsesmart.czsourced159 tok/s
empty context, 128 generated
—sourced115 tok/ssourced9870 tok/s
at 4K

Setup: run Qwen 3 30B-A3B on a Mac

Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-11-14:

ollama run qwen3:30b-a3b

MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:

pip install -U mlx-lm
mlx_lm.generate --model <repo-id> --prompt "Hello"

Downloads: Ollama page → · Hugging Face model card →

The 162 tok/s figure above came from MLX at 4-bit; other runtimes and quants run at different speeds.

Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.

Qwen 3 30B-A3B on other Apple Silicon chips

ChipSpeedQuantEngineBandwidth
M5 Maxsourced152 tok/s4-bitMLX614 GB/s
M4 Maxsourced90 tok/s4-bitllama.cpp546 GB/s
M3 Maxestimated75 tok/sQ4_K_MOllama400 GB/s
M6sourced62 tok/squantization not statedMLX170 GB/s
M4 Proestimated58 tok/sQ4_K_MMLX273 GB/s

For the estimated figures here, the bandwidth formula’s typical error for small MoEs (≤40B total) is ±15%, against 88 measured runs of 15 models (how it is computed).

About Qwen 3 30B-A3B

Alibaba's Apache 2.0 30B MoE with 3B active. It fits a 24 GB Mac at 4-bit; tbreak's reviews measured 130.6 tok/s on an M5 Max and 62.0 on a Mac mini M6 (MLX, quantization not stated).

Apache 2.0 licence · 30B MoE · 128K context · LLMCheck capability 22/50 · see its leaderboard rank →

Memory by context length

Estimated, not measured: the index’s minimum for Qwen 3 30B-A3B (18 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. GQA on all 48 layers (4 kv heads x 128). A 16-bit KV cache is the default in llama.cpp, Ollama, LM Studio and mlx-lm; a q8 cache halves the KV part. Coding agents hold 64K tokens or more. Runtimes also add a buffer that grows with context, so leave a few GB spare. macOS lets the GPU use only part of a Mac’s memory by default (figures for an M5 Ultra Mac, which runs macOS 26 or later): “fits” means within the GPU memory a Mac of that tier can use with the limit raised, a tier tagged raise GPU limit fits only after sudo sysctl iogpu.wired_limit_mb raises it (the tooltip has the exact command), and the last column is the smallest Mac memory size whose default limit holds it (the GPU memory limit).

ContextKV cache (16-bit)RAM neededRAM, q8 KVSmallest tier that fitsWithin the default GPU limit
8K~0.8 GB~18.4 GB~18.2 GB24 GB Mac raise GPU limit32 GB Mac
32K~3.2 GB~20.8 GB~19.4 GB32 GB Macsame
64K (coding-agent context)~6.4 GB~24.0 GB~21.0 GB32 GB Macsame
128K~12.9 GB~30.5 GB~24.2 GB64 GB Mac48 GB Mac

System requirements

Macs with the M5 Ultra

🛒 Get a Mac that runs Qwen 3 30B-A3B

Qwen 3 30B-A3B needs about 18 GB of unified memory. These Apple Silicon Macs have enough to run it. Apple builds the higher-memory configurations to order; Amazon does not stock them.

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how Qwen 3 30B-A3B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard