Can I run Qwen3.8-27B on a Mac?

Yes: Qwen3.8-27B runs on 43 of the 54 Macs in the LLMCheck index. It needs about 19 GB at a 4K context, 24 GB at 64K. Smallest current Mac: Mac mini M6 24 GB (raised GPU limit); cheapest at 15+ tok/s: Mac mini M5 Pro 24 GB, $1,699 (raised limit). Best measured figure: 55 tok/s on an M5 Ultra (published).

RAM at 4K
19
GB
RAM at 64K
24
GB, 16-bit KV
Macs that run it
43
of 54 configs
Best measured
sourced55
tok/s · M5 Ultra

Qwen3.8-27B on every Mac

One row per Mac configuration, grouped by product line. The build is the one each speed is for; the context column is the longest prompt that fits inside macOS’s default GPU memory limit with a 16-bit KV cache (“raised” where the limit has to be raised first; “full” when the whole window fits). Speeds are decode tok/s from the LLMCheck index, each with its provenance mark. For dense models, the formula’s typical error is about 9% (the median gap to 75 measured plain-decode runs; it tends to undershoot (median −6%), and an estimate scaled from the model’s own measured run is usually closer; method).

Runs fits macOS’s default GPU limit, 15+ tok/sRuns, slowly fits, under 15 tok/sRaise GPU limit fits once the limit is raised (command below)Doesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBDoesn't fit————
MacBook Air M5 24 GBRaise GPU limit command ↓Q4_K_Mestimated8 tok/s18K raised—
MacBook Air M5 32 GBRuns, slowlyQ4_K_Mestimated8 tok/s92K—
MacBook Air M1 8 GB refurbDoesn't fit————
MacBook Air M4 16 GB usedDoesn't fit————
MacBook Air M2 16 GB refurbDoesn't fit————
MacBook Air M3 16 GB refurbDoesn't fit————
MacBook Air M1 16 GB refurbDoesn't fit————
MacBook Air M4 24 GB usedRaise GPU limit command ↓Q4_K_Mestimated7 tok/s18K raised—
MacBook Air M2 24 GB refurbRaise GPU limit command ↓Q4_K_Mestimated5 tok/s18K raised—
MacBook Air M3 24 GB refurbRaise GPU limit command ↓Q4_K_Mestimated5 tok/s18K raised—
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBRaise GPU limit command ↓4-bitsourced17 tok/s18K raisedM5 Pro page
MacBook Pro M6 24 GBRaise GPU limit command ↓4-bitcommunity10 tok/s18K raisedM6 page
MacBook Pro M6 32 GBRuns, slowly4-bitcommunity10 tok/s92KM6 page
MacBook Pro M5 Pro 48 GBRuns4-bitsourced17 tok/s256K (full)M5 Pro page
MacBook Pro M5 Max 64 GBRuns4-bitcommunity31 tok/s256K (full)M5 Max page
MacBook Pro M5 Pro 64 GBRuns4-bitsourced17 tok/s256K (full)M5 Pro page
MacBook Pro M5 Max 128 GBRuns4-bitcommunity31 tok/s256K (full)M5 Max page
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated19 tok/s256K (full)M3 Max page
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated19 tok/s256K (full)M3 Max page
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBRaise GPU limit command ↓4-bitsourced17 tok/s18K raisedM5 Pro page
Mac mini M6 24 GBRaise GPU limit command ↓4-bitcommunity10 tok/s18K raisedM6 page
Mac mini M6 32 GBRuns, slowly4-bitcommunity10 tok/s92KM6 page
Mac mini M5 Pro 48 GBRuns4-bitsourced17 tok/s256K (full)M5 Pro page
Mac mini M5 Pro 64 GBRuns4-bitsourced17 tok/s256K (full)M5 Pro page
Mac mini M2 Pro 16 GB refurbDoesn't fit————
Mac mini M4 16 GB usedDoesn't fit————
Mac mini M4 Pro 24 GB usedRaise GPU limit command ↓Q4_K_Mestimated13 tok/s18K raisedM4 Pro page
Mac mini M4 24 GB usedRaise GPU limit command ↓Q4_K_Mestimated7 tok/s18K raised—
Mac mini M2 Pro 32 GB refurbRuns, slowlyQ4_K_Mestimated11 tok/s38K—
Mac mini M4 Pro 48 GB usedRuns, slowlyQ4_K_Mestimated13 tok/s256K (full)M4 Pro page
Mac mini M4 Pro 64 GB usedRuns, slowlyQ4_K_Mestimated13 tok/s256K (full)M4 Pro page
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBRaise GPU limit command ↓4-bitcommunity10 tok/s18K raisedM6 page
iMac M6 32 GBRuns, slowly4-bitcommunity10 tok/s92KM6 page
Mac Studio
Mac Studio M5 Max 36 GBRunsQ4_K_Mestimated24 tok/s139KM5 Max page
Mac Studio M5 Max 48 GBRuns4-bitcommunity31 tok/s256K (full)M5 Max page
Mac Studio M5 Max 64 GBRuns4-bitcommunity31 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 96 GBRunsoQ4esourced48 tok/s256K (full)M5 Ultra page
Mac Studio M5 Max 128 GBRuns4-bitcommunity31 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 256 GBRunsoQ4esourced48 tok/s256K (full)M5 Ultra page
Mac Studio M5 Ultra 512 GBRunsoQ4esourced48 tok/s256K (full)M5 Ultra page
Mac Studio M2 Max 32 GB refurbRunsQ4_K_Mestimated21 tok/s38K—
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated38 tok/s256K (full)—
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated26 tok/s256K (full)M4 Max page
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated21 tok/s256K (full)—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated38 tok/s256K (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated38 tok/s256K (full)—
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated26 tok/s256K (full)M4 Max page
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated38 tok/s256K (full)—
Mac Studio M3 Ultra 256 GB usedRuns4-bitcommunity38 tok/s256K (full)M3 Ultra page
Mac Studio M3 Ultra 512 GB refurbRuns4-bitcommunity38 tok/s256K (full)M3 Ultra page
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Context memory is computed from its config.json (hybrid: full attention on 16 of 64 layers; Gated DeltaNet layers keep a constant state): about 4.3 GB of 16-bit KV cache at 64K tokens. A q8 cache (llama.cpp -ctk q8_0 -ctv q8_0, Ollama OLLAMA_KV_CACHE_TYPE=q8_0) halves that part. Runtimes also grow a compute buffer with context, so a fit within about 1 GB of the limit is optimistic.

Raising the GPU memory limit

macOS lets the GPU wire only part of unified memory by default (Metal’s recommended working set; M5 and M6 Macs run macOS 26 or later, whose default is higher), and Qwen3.8-27B needs about 19 GB. On the Macs marked Raise GPU limit it fits in RAM but not inside that default. The default is a performance threshold, not a hard wall: past it, the runtime moves part of it to the CPU or shortens the context (llama.cpp, Ollama), runs it slowly (MLX), or stops with an out-of-memory error. One command raises the limit until the next restart (sudo sysctl iogpu.wired_limit_mb=0 restores the default sooner); it leaves macOS a reserve, and other apps get less memory while the model is loaded.

Qwen3.8-27B: memory by quantization

Weights are 27.8B parameters at each format’s effective size (the index’s GB-per-billion table), plus about 2 GB for the runtime and a short context; longer contexts add the KV cache computed from the model’s config.json at 16 bits. The first row is the catalog’s own figure (about 19 GB at a 4K context), the one every verdict on this page uses. “Smallest Mac” is the smallest memory size among the Macs Apple sells new that holds it at a 4K context inside that Mac’s default GPU limit. Estimates, not measurements.

BuildWeightsRAM at 4Kat 32Kat 64KSmallest Mac
As catalogued—19 GB21 GB23 GB32 GB (24 GB with a raised limit)
Q2_K9.5 GB11 GB13 GB15 GB16 GB
Q3_K_M13.6 GB16 GB18 GB20 GB24 GB
Q4_K_M15.8 GB18 GB20 GB22 GB32 GB (24 GB with a raised limit)
Q5_K_M19.7 GB22 GB24 GB26 GB32 GB
Q6_K22.8 GB25 GB27 GB29 GB32 GB
Q8_029.5 GB31 GB33 GB35 GB48 GB (36 GB with a raised limit)
F1655.6 GB58 GB59 GB62 GB96 GB

Measured runs of Qwen3.8-27B

Every published (filled square) and community (hollow circle) run the index holds for Qwen3.8-27B: 8 published, 14 community, each linked to its source. LLMCheck runs no tests of its own. One row is one measurement session; on each chip the table above shows the lower median of the eligible runs (plain decode at 5 bits or fewer), and a binned or “not an anchor” run is shown but never used as a reference.

ChipRuntimeQuantDecodeContextDateSource
M5 Ultra 256 GBLM StudioQ4_K_Msourced55 tok/s—2026-09bgr.com
M5 Ultra 256 GBMLX4-bitcommunity54.7 tok/s512-token prompt, 128 generated2026-09-20github.com
M5 Ultra 256 GBMLXoQ4esourced48 tok/s6,091-token prompt2026-09macstories.net
M5 Ultra 256 GBllama.cppQ4_K_Msourced46.27 tok/sISL 2048 / OSL 512, depth 02026-09-21tomshardware.com
M5 Ultra 512 GBMLXBF16sourced19.69 tok/s8,192-token context, 128 generated2026-10-15machinelearning.apple.com
M3 Ultra 96 GBLM StudioQ4_K_Msourced40 tok/s—2026-09bgr.com
M3 Ultra 512 GBMLX4-bitcommunity37.6 tok/s512-token prompt, 128 generated2026-09-20github.com
M3 Ultra 512 GBMLXoQ4esourced31 tok/s6,091-token prompt2026-09macstories.net
M3 Ultra 512 GBMLXBF16sourced12.46 tok/s8,192-token context, 128 generated2026-10-15machinelearning.apple.com
M5 Max 128 GBLM Studio4-bitcommunity32.9 tok/s512-token coding answer after a short prompt, median of 5 at T 0.62026-10-25github.com
M5 Max 128 GBMLX4-bitcommunity31 tok/s512-token coding answer after a short prompt, median of 5 at T 0.62026-10-25github.com
M5 Max 128 GBMLX8-bitcommunity17.9 tok/sshort prompt, 400 tokens2026-08-20github.com
M1 Max 64 GBLM Studio8-bitcommunity11.38 tok/s41-token chat prompt, 541 generated, thinking on (medium)2026-10-08github.com
M5 Pro 48 GBLM Studio4-bitcommunity16.81 tok/s512-token coding answers, median of 5 at T 0.62026-10-19github.com
M5 Pro 48 GBllama.cpp4-bitsourced16.5 tok/ssingle stream; prompt length not stated2026-10-15frandroid.com
M5 Pro 48 GBMLX4-bitcommunity16.33 tok/s512-token coding answers, median of 5 at T 0.62026-10-19github.com
M6 32 GBMLXDWQcommunity11.5 tok/s~20-token chat prompt, up to 400 generated2026-10-28github.com
M6 32 GBMLXMXFP4community10.2 tok/s~20-token chat prompt, up to 400 generated2026-10-28github.com
M6 24 GBMLX4-bitcommunity9.8 tok/s525-token prompt2026-10-09llamaperf.com not an anchor
M6 32 GBMLX4-bitcommunity9.8 tok/s1k2026-11-05omlx.ai
M6 32 GBMLX4-bitcommunity9.7 tok/s~20-token chat prompt, up to 400 generated2026-10-28github.com
M6 24 GBLM StudioQATcommunity9.42 tok/sshort prompt2026-09-22nyaa.sh

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 18 GB):

ollama run qwen3.8:27b

Prefer a window to a terminal? LM Studio downloads the same model with one click. · model card →

On the Mac mini M6 (32 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is 10 tok/s (community run) at 4-bit; keep the context at or under 92K there, or use a q8 KV cache. The qwen3.8:27b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Qwen3.8-27B

Mac mini M6 (24 GB) — smallest current Mac that runs it, $1,099 new (Apple list price, checked 2026-11-14), 10 tok/s (community run) once the GPU memory limit is raised. Mac mini M5 Pro (24 GB) — cheapest at 15+ tok/s, $1,699 new (Apple list price, checked 2026-11-14), 17 tok/s (published figure) once the GPU memory limit is raised.

As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence the verdicts.

FAQ: Qwen3.8-27B on a Mac

Can I run Qwen3.8-27B on a Mac?

Yes. Qwen3.8-27B needs about 19 GB of unified memory at a short (4K-token) context, so it runs on 43 of the 54 Mac configurations in the LLMCheck index; 32 of them hold it inside macOS’s default GPU memory limit and 11 only after raising that limit. The smallest Mac Apple sells new that runs it is the Mac mini M6 (24 GB).

How much RAM does Qwen3.8-27B need?

About 19 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 21 GB in total at 32K and 24 GB at 64K with the default 16-bit cache (about 22 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Qwen3.8-27B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is 31 tok/s (community run) at 4-bit. The best measured figure is 55 tok/s on an M5 Ultra 256 GB (published figure, Q4_K_M). Every Mac’s figure is in the table on this page with its provenance: published, community run or estimated.

What is the cheapest Mac that runs Qwen3.8-27B well?

Among Macs Apple sells new, the Mac mini M5 Pro (24 GB), $1,699 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Qwen3.8-27B, at 17 tok/s (published figure), after raising the GPU memory limit.

Do I need to raise the GPU memory limit to run Qwen3.8-27B?

On 11 of the 54 configurations, yes: iMac M6 24 GB, Mac mini M5 Pro 24 GB, Mac mini M6 24 GB and 8 more. macOS lets the GPU use only part of unified memory by default (about 18 GB on the iMac M6 (24 GB)), and Qwen3.8-27B needs about 19 GB. Running sudo sysctl iogpu.wired_limit_mb=20480 in Terminal raises the limit on a 24 GB Mac until the next restart. From 32 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of Qwen3.8-27B should I use?

Q4_K_M (about 16 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 29 GB) is closer to full quality and needs a 48 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 14 and 9 GB at a quality cost. The index’s reference figure (31 tok/s on an M5 Max) is for its 4-bit build.

How much context can Qwen3.8-27B use on a Mac?

Its own window is 256K tokens. At macOS’s default GPU limit, the Mac mini M6 (32 GB) holds about 92K. The full window needs about 36 GB, which a 48 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.

Cite this page

LLMCheck. (2026). Can I run Qwen3.8-27B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/qwen38-27b/ (updated ). CC BY 4.0.

How to cite LLMCheck →Data: CC BY 4.0Markdown version

Related

Figures from the LLMCheck index, data version 2026-11-18. Verdicts and context limits are estimates from each model’s catalog memory figure and config.json.