Can I run Mistral Medium 3.5 on a Mac?

Yes: Mistral Medium 3.5 runs on 12 of 54 Macs in the LLMCheck index. It needs about 77 GB at a 4K context, 100 GB at 64K. Smallest and fastest current Mac: the Mac Studio M5 Ultra 96 GB (~13 tok/s est.); none reaches 15 tok/s. Best measured figure: 7.7 tok/s on an M5 Ultra 512 GB (published figure, FP8).

RAM at 4K
77
GB
RAM at 64K
100
GB, 16-bit KV
Macs that run it
12
of 54 configs
Best measured
sourced7.7
tok/s · M5 Ultra

Mistral Medium 3.5 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 GBDoesn't fit————
MacBook Air M5 32 GBDoesn't fit————
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 usedDoesn't fit————
MacBook Air M2 24 GB refurbDoesn't fit————
MacBook Air M3 24 GB refurbDoesn't fit————
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBDoesn't fit————
MacBook Pro M6 24 GBDoesn't fit————
MacBook Pro M6 32 GBDoesn't fit————
MacBook Pro M5 Pro 48 GBDoesn't fit————
MacBook Pro M5 Max 64 GBDoesn't fit————
MacBook Pro M5 Pro 64 GBDoesn't fit————
MacBook Pro M5 Max 128 GBRuns, slowlyQ4_K_Mestimated7 tok/s86KM5 Max page
MacBook Pro M3 Max 64 GB refurbDoesn't fit————
MacBook Pro M3 Max 128 GB refurbRuns, slowlyQ4_K_Mestimated4 tok/s55K—
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBDoesn't fit————
Mac mini M6 24 GBDoesn't fit————
Mac mini M6 32 GBDoesn't fit————
Mac mini M5 Pro 48 GBDoesn't fit————
Mac mini M5 Pro 64 GBDoesn't fit————
Mac mini M2 Pro 16 GB refurbDoesn't fit————
Mac mini M4 16 GB usedDoesn't fit————
Mac mini M4 Pro 24 GB usedDoesn't fit————
Mac mini M4 24 GB usedDoesn't fit————
Mac mini M2 Pro 32 GB refurbDoesn't fit————
Mac mini M4 Pro 48 GB usedDoesn't fit————
Mac mini M4 Pro 64 GB usedDoesn't fit————
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBDoesn't fit————
iMac M6 32 GBDoesn't fit————
Mac Studio
Mac Studio M5 Max 36 GBDoesn't fit————
Mac Studio M5 Max 48 GBDoesn't fit————
Mac Studio M5 Max 64 GBDoesn't fit————
Mac Studio M5 Ultra 96 GBRuns, slowlyQ4_K_Mestimated13 tok/s6KM5 Ultra page
Mac Studio M5 Max 128 GBRuns, slowlyQ4_K_Mestimated7 tok/s86KM5 Max page
Mac Studio M5 Ultra 256 GBRuns, slowlyQ4_K_Mestimated13 tok/s256K (full)M5 Ultra page
Mac Studio M5 Ultra 512 GBRuns, slowlyQ4_K_Mestimated13 tok/s256K (full)M5 Ultra page
Mac Studio M2 Max 32 GB refurbDoesn't fit————
Mac Studio M1 Ultra 64 GB refurbDoesn't fit————
Mac Studio M4 Max 64 GB usedDoesn't fit————
Mac Studio M2 Max 64 GB refurbDoesn't fit————
Mac Studio M1 Ultra 128 GB refurbRuns, slowlyQ4_K_Mestimated9 tok/s55K—
Mac Studio M2 Ultra 128 GB refurbRuns, slowlyQ4_K_Mestimated9 tok/s55K—
Mac Studio M4 Max 128 GB usedRuns, slowlyQ4_K_Mestimated6 tok/s55K—
Mac Studio M2 Ultra 192 GB refurbRuns, slowlyQ4_K_Mestimated9 tok/s185K—
Mac Studio M3 Ultra 256 GB usedRuns, slowlyQ4_K_Mestimated9 tok/s256K (full)M3 Ultra page
Mac Studio M3 Ultra 512 GB refurbRuns, slowlyQ4_K_Mestimated9 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 (GQA on all 88 layers (8 kv heads x 128)): about 23.6 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.

macOS’s GPU memory limit

macOS lets the GPU use only part of unified memory by default. Mistral Medium 3.5 fits inside that default limit on every Mac it fits at all, so no Mac in the table needs it raised at a short context. Long contexts may still need it: the context column already uses each Mac’s default limit.

Mistral Medium 3.5: memory by quantization

Weights are 128B 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 77 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—77 GB87 GB99 GB96 GB
Q2_K43.5 GB46 GB56 GB68 GB64 GB
Q3_K_M62.7 GB65 GB75 GB87 GB96 GB
Q4_K_M73.0 GB75 GB85 GB97 GB96 GB
Q5_K_M90.9 GB93 GB103 GB115 GB128 GB
Q6_K105.0 GB107 GB117 GB129 GB128 GB
Q8_0135.7 GB138 GB148 GB160 GB256 GB
F16256.0 GB258 GB268 GB280 GB512 GB

Measured runs of Mistral Medium 3.5

Every published (filled square) and community (hollow circle) run the index holds for Mistral Medium 3.5: 2 published, 0 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 512 GBMLXFP8sourced7.7 tok/s8,192-token context, 128 generated2026-10-15machinelearning.apple.com
M3 Ultra 512 GBMLXFP8sourced4.95 tok/s8,192-token context, 128 generated2026-10-15machinelearning.apple.com

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 80 GB):

ollama run mistral-medium-3.5:128b

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

On the Mac Studio M5 Ultra (96 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~13 tok/s (estimated) at Q4_K_M; keep the context at or under 6K there, or use a q8 KV cache. The mistral-medium-3.5:128b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Mistral Medium 3.5

Mac Studio M5 Ultra (96 GB) — smallest current Mac that runs it, $5,499 new (Apple list price, checked 2026-11-14), ~13 tok/s (estimated). Amazon does not stock the Mac Studio M5 Ultra (96 GB): Apple builds it to order.

FAQ: Mistral Medium 3.5 on a Mac

Can I run Mistral Medium 3.5 on a Mac?

Yes. Mistral Medium 3.5 needs about 77 GB of unified memory at a short (4K-token) context, so it runs on 12 of the 54 Mac configurations in the LLMCheck index. The smallest Mac Apple sells new that runs it is the Mac Studio M5 Ultra (96 GB).

How much RAM does Mistral Medium 3.5 need?

About 77 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 88 GB in total at 32K and 100 GB at 64K with the default 16-bit cache (about 89 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Mistral Medium 3.5 run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~7 tok/s (estimated) at Q4_K_M. The best measured figure is 7.7 tok/s on an M5 Ultra 512 GB (published figure, FP8). 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 Mistral Medium 3.5 well?

No Mac Apple sells new reaches 15 tok/s with Mistral Medium 3.5. The fastest is the Mac Studio M5 Ultra (96 GB) at ~13 tok/s (estimated): fine for batch work, slow for chat.

Do I need to raise the GPU memory limit to run Mistral Medium 3.5?

No. On all 12 Mac configurations where Mistral Medium 3.5 fits, it fits inside that Mac’s default GPU memory limit at a short context; only a long context on the smallest of them can push it over.

Which quantization of Mistral Medium 3.5 should I use?

Q4_K_M (about 73 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 136 GB) is closer to full quality and needs a 256 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 63 and 44 GB at a quality cost. The index’s reference figure (7 tok/s on an M5 Max) is for its Q4_K_M build.

How much context can Mistral Medium 3.5 use on a Mac?

Its own window is 256K tokens. At macOS’s default GPU limit, the Mac Studio M5 Ultra (96 GB) holds about 6K. The full window needs about 171 GB, which a 256 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.

Cite this page

LLMCheck. (2026). Can I run Mistral Medium 3.5 on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/mistral-medium-35/ (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.