Can I run Qwen 3.5 9B on a Mac?

Yes: Qwen 3.5 9B runs on 53 of 54 Macs in the LLMCheck index. It needs about 7 GB at a 4K context, 10 GB at 64K. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac mini M6 16 GB ($899; 30 tok/s community-measured). Best measured figure: 167 tok/s on an M5 Ultra (community).

RAM at 4K
7
GB
RAM at 64K
10
GB, 16-bit KV
Macs that run it
53
of 54 configs
Best measured
community167
tok/s · M5 Ultra

Qwen 3.5 9B 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)Over GPU limit fits RAM on paper, but even a safe raise is shortDoesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBRunsQ4_K_Mestimated27 tok/s148K—
MacBook Air M5 24 GBRunsQ4_K_Mestimated27 tok/s256K (full)—
MacBook Air M5 32 GBRunsQ4_K_Mestimated27 tok/s256K (full)—
MacBook Air M1 8 GB refurbOver GPU limit why ↓Q4_K_Mestimated10 tok/s—M1 page
MacBook Air M4 16 GB usedRunsQ4_K_Mestimated18 tok/s113KM4 page
MacBook Air M2 16 GB refurbRunsQ4_K_Mestimated15 tok/s113K—
MacBook Air M3 16 GB refurbRunsQ4_K_Mestimated15 tok/s113KM3 page
MacBook Air M1 16 GB refurbRuns, slowlyQ4_K_Mestimated10 tok/s113KM1 page
MacBook Air M4 24 GB usedRunsQ4_K_Mestimated18 tok/s256K (full)M4 page
MacBook Air M2 24 GB refurbRunsQ4_K_Mestimated15 tok/s256K (full)—
MacBook Air M3 24 GB refurbRunsQ4_K_Mestimated15 tok/s256K (full)M3 page
MacBook Pro
MacBook Pro M6 16 GBRuns4-bitcommunity30 tok/s148KM6 page
MacBook Pro M5 Pro 24 GBRunsQ4_K_Mestimated56 tok/s256K (full)—
MacBook Pro M6 24 GBRunsQ4_K_Mestimated30 tok/s256K (full)M6 page
MacBook Pro M6 32 GBRunsQ4_K_Mestimated30 tok/s256K (full)M6 page
MacBook Pro M5 Pro 48 GBRunsQ4_K_Mestimated56 tok/s256K (full)—
MacBook Pro M5 Max 64 GBRunsQ4_K_Mestimated81 tok/s256K (full)M5 Max page
MacBook Pro M5 Pro 64 GBRunsQ4_K_Mestimated56 tok/s256K (full)—
MacBook Pro M5 Max 128 GBRunsQ4_K_Mestimated81 tok/s256K (full)M5 Max page
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated63 tok/s256K (full)—
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated63 tok/s256K (full)—
Mac mini
Mac mini M6 16 GBRuns4-bitcommunity30 tok/s148KM6 page
Mac mini M5 Pro 24 GBRunsQ4_K_Mestimated56 tok/s256K (full)—
Mac mini M6 24 GBRunsQ4_K_Mestimated30 tok/s256K (full)M6 page
Mac mini M6 32 GBRunsQ4_K_Mestimated30 tok/s256K (full)M6 page
Mac mini M5 Pro 48 GBRunsQ4_K_Mestimated56 tok/s256K (full)—
Mac mini M5 Pro 64 GBRunsQ4_K_Mestimated56 tok/s256K (full)—
Mac mini M2 Pro 16 GB refurbRunsQ4_K_Mestimated35 tok/s113K—
Mac mini M4 16 GB usedRunsQ4_K_Mestimated18 tok/s113KM4 page
Mac mini M4 Pro 24 GB usedRunsQ4_K_Mcommunity39 tok/s256K (full)M4 Pro page
Mac mini M4 24 GB usedRunsQ4_K_Mestimated18 tok/s256K (full)M4 page
Mac mini M2 Pro 32 GB refurbRunsQ4_K_Mestimated35 tok/s256K (full)—
Mac mini M4 Pro 48 GB usedRunsQ4_K_Mcommunity39 tok/s256K (full)M4 Pro page
Mac mini M4 Pro 64 GB usedRunsQ4_K_Mcommunity39 tok/s256K (full)M4 Pro page
iMac
iMac M6 16 GBRuns4-bitcommunity30 tok/s148KM6 page
iMac M6 24 GBRunsQ4_K_Mestimated30 tok/s256K (full)M6 page
iMac M6 32 GBRunsQ4_K_Mestimated30 tok/s256K (full)M6 page
Mac Studio
Mac Studio M5 Max 36 GBRunsQ4_K_Mestimated63 tok/s256K (full)M5 Max page
Mac Studio M5 Max 48 GBRunsQ4_K_Mestimated81 tok/s256K (full)M5 Max page
Mac Studio M5 Max 64 GBRunsQ4_K_Mestimated81 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 96 GBRuns4-bitcommunity167 tok/s256K (full)M5 Ultra page
Mac Studio M5 Max 128 GBRunsQ4_K_Mestimated81 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 256 GBRuns4-bitcommunity167 tok/s256K (full)M5 Ultra page
Mac Studio M5 Ultra 512 GBRuns4-bitcommunity167 tok/s256K (full)M5 Ultra page
Mac Studio M2 Max 32 GB refurbRunsQ4_K_Mestimated63 tok/s256K (full)—
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated81 tok/s256K (full)—
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated73 tok/s256K (full)—
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated63 tok/s256K (full)—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated81 tok/s256K (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated81 tok/s256K (full)—
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated73 tok/s256K (full)—
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated81 tok/s256K (full)—
Mac Studio M3 Ultra 256 GB usedRunsQ4_K_Mcommunity81 tok/s256K (full)M3 Ultra page
Mac Studio M3 Ultra 512 GB refurbRunsQ4_K_Mcommunity81 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 8 of 32 layers; Gated DeltaNet layers keep a constant state): about 2.1 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 Qwen 3.5 9B needs about 7 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. On the Macs marked Over GPU limit even that raise falls short: the model fits the Mac’s RAM on paper, but a smaller quant or a bigger Mac is the realistic route.

Qwen 3.5 9B: memory by quantization

Weights are 9B 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 7 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—7 GB8 GB9 GB16 GB
Q2_K3.1 GB5 GB6 GB7 GB16 GB
Q3_K_M4.4 GB6 GB7 GB8 GB16 GB
Q4_K_M5.1 GB7 GB8 GB9 GB16 GB
Q5_K_M6.4 GB8 GB9 GB10 GB16 GB
Q6_K7.4 GB9 GB10 GB11 GB16 GB
Q8_09.5 GB12 GB12 GB14 GB16 GB
F1618.0 GB20 GB21 GB22 GB32 GB (24 GB with a raised limit)

Measured runs of Qwen 3.5 9B

Every published (filled square) and community (hollow circle) run the index holds for Qwen 3.5 9B: 0 published, 6 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 GBMLX4-bitcommunity167 tok/s512-token random prompt, 128 generated, empty context, mean of 22026-10-15bohemiansilicon.com
M3 Ultra 96 GBMLX4-bitcommunity114.1 tok/s75-token chat prompt, three greedy 256-token continuations2026-11-07github.com
M3 Ultra 96 GBllama.cppQ4_K_Mcommunity81 tok/s75-token chat prompt, three greedy 256-token continuations2026-11-07github.com
M4 Pro 48 GBMLX4-bitcommunity50.2 tok/s75-token chat prompt, three greedy 256-token continuations2026-11-07github.com
M4 Pro 48 GBllama.cppQ4_K_Mcommunity39.1 tok/s75-token chat prompt, three greedy 256-token continuations2026-11-07github.com
M6 16 GBMLX4-bitcommunity29.8 tok/s1k2026-11-03omlx.ai binned

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 7.6 GB):

ollama run qwen3.5:9b

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

On the Mac mini M6 (16 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is 30 tok/s (community run) at 4-bit; keep the context at or under 148K there, or use a q8 KV cache. The qwen3.5:9b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Qwen 3.5 9B

Mac mini M6 (16 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $899 new (Apple list price, checked 2026-11-14), 30 tok/s (community run).

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

FAQ: Qwen 3.5 9B on a Mac

Can I run Qwen 3.5 9B on a Mac?

Yes. Qwen 3.5 9B needs about 7 GB of unified memory at a short (4K-token) context, so it runs on 53 of the 54 Mac configurations in the LLMCheck index. On 1 more it fits the RAM, but not even a safely raised GPU limit. The smallest Mac Apple sells new that runs it is the Mac mini M6 (16 GB).

How much RAM does Qwen 3.5 9B need?

About 7 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 8 GB in total at 32K and 10 GB at 64K with the default 16-bit cache (about 9 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Qwen 3.5 9B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~81 tok/s (estimated) at Q4_K_M. The best measured figure is 167 tok/s on an M5 Ultra 256 GB (community run, 4-bit). 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 Qwen 3.5 9B well?

Among Macs Apple sells new, the Mac mini M6 (16 GB), $899 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Qwen 3.5 9B, at 30 tok/s (community run).

Do I need to raise the GPU memory limit to run Qwen 3.5 9B?

On MacBook Air M1 8 GB (used) even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 16 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of Qwen 3.5 9B should I use?

Q4_K_M (about 5 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 10 GB) is closer to full quality and needs a 16 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 4 and 3 GB at a quality cost. The index’s reference figure (81 tok/s on an M5 Max) is for its Q4_K_M build.

How much context can Qwen 3.5 9B use on a Mac?

Its own window is 256K tokens. At macOS’s default GPU limit, the Mac mini M6 (16 GB) holds about 148K. The full window needs about 16 GB, which a 24 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.

Cite this page

LLMCheck. (2026). Can I run Qwen 3.5 9B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/qwen-35-9b/ (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.