Yes: DeepSeek V3.2-Speciale runs on 2 of the 54 Macs in the LLMCheck index. It needs about 360 GB of unified memory at a 4K context and about 365 GB at 64K. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac Studio M5 Ultra 512 GB ($22,299; ~18 tok/s est.). No measured run yet.
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 large mixture-of-experts models (over 40B total), the formula’s typical error is about 34% (the median gap to 70 measured plain-decode runs; it tends to undershoot (median −33%), and an estimate scaled from the model’s own measured run is usually closer; method).
| Mac | Verdict | Build | Speed | Max context | Model page |
|---|---|---|---|---|---|
| MacBook Air | |||||
| MacBook Air M5 16 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 24 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 32 GB | Doesn't fit | — | — | — | — |
| MacBook Air M1 8 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 16 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M1 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 24 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro | |||||
| MacBook Pro M6 16 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 32 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 64 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 64 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 128 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M3 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro M3 Max 128 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini | |||||
| Mac mini M6 16 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 32 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 64 GB | Doesn't fit | — | — | — | — |
| Mac mini M2 Pro 16 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 16 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M2 Pro 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 48 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 64 GB used | Doesn't fit | — | — | — | — |
| iMac | |||||
| iMac M6 16 GB | Doesn't fit | — | — | — | — |
| iMac M6 24 GB | Doesn't fit | — | — | — | — |
| iMac M6 32 GB | Doesn't fit | — | — | — | — |
| Mac Studio | |||||
| Mac Studio M5 Max 36 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 48 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 64 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Ultra 96 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 128 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Ultra 256 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Ultra 512 GB | Runs | Q4_K_M | estimated18 tok/s | 128K (full) | — |
| Mac Studio M2 Max 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M4 Max 64 GB used | Doesn't fit | — | — | — | — |
| Mac Studio M2 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 128 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M2 Ultra 128 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M4 Max 128 GB used | Doesn't fit | — | — | — | — |
| Mac Studio M2 Ultra 192 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M3 Ultra 256 GB used | Doesn't fit | — | — | — | — |
| Mac Studio M3 Ultra 512 GB refurb | Runs, slowly | Q4_K_M | estimated12 tok/s | 128K (full) | — |
Context memory is computed from its config.json (MLA on all 61 layers (kv_lora_rank 512 + rope 64); DSA lightning-indexer keys (index_head_dim per layer) not counted; runtimes that expand MLA to per-head K/V use far more): about 4.6 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 lets the GPU use only part of unified memory by default. DeepSeek V3.2-Speciale 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.
Weights are 685B 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. It is a mixture-of-experts model: all 685B parameters sit in memory although only 37B are read per token. The first row is the catalog’s own figure (about 360 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.
| Build | Weights | RAM at 4K | at 32K | at 64K | Smallest Mac |
|---|---|---|---|---|---|
| As catalogued | — | 360 GB | 362 GB | 364 GB | 512 GB |
| Q2_K | 232.9 GB | 235 GB | 237 GB | 239 GB | 512 GB |
| Q3_K_M | 335.6 GB | 338 GB | 340 GB | 342 GB | 512 GB |
| Q4_K_M | 390.4 GB | 392 GB | 394 GB | 397 GB | 512 GB |
| Q5_K_M | 486.3 GB | 488 GB | 490 GB | 493 GB | 512 GB |
| Q6_K | 561.7 GB | 564 GB | 566 GB | 568 GB | |
| Q8_0 | 726.1 GB | 728 GB | 730 GB | 732 GB | |
| F16 | 1370.0 GB | 1372 GB | 1374 GB | 1376 GB |
The index holds no published or community run of DeepSeek V3.2-Speciale yet, so every speed on this page is an estimate from the memory-bandwidth model. LLMCheck runs no tests of its own: if you have run it on a Mac, submit the figure with its setup →
The index has no verified Ollama tag for DeepSeek V3.2-Speciale. Start from its listing and copy the exact name of a build that fits: Search the Ollama library → · model card →
GGUF builds run in LM Studio or llama.cpp; MLX builds run in LM Studio or mlx-lm.
On the Mac Studio M5 Ultra (512 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~18 tok/s (estimated) at Q4_K_M; keep the context at or under 128K there, or use a q8 KV cache.
Step-by-step: the Ollama install guide.
Mac Studio M5 Ultra (512 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $22,299 new (Apple list price, checked 2026-11-14), ~18 tok/s (estimated). Amazon does not stock the Mac Studio M5 Ultra (512 GB): Apple builds it to order.
Yes. DeepSeek V3.2-Speciale needs about 360 GB of unified memory at a short (4K-token) context, so it runs on 2 of the 54 Mac configurations in the LLMCheck index. The smallest Mac Apple sells new that runs it is the Mac Studio M5 Ultra (512 GB).
About 360 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 363 GB in total at 32K and 365 GB at 64K with the default 16-bit cache (about 363 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.
On an M5 Ultra, the chip the leaderboard quotes it on, the index figure is ~18 tok/s (estimated) at Q4_K_M. No published or community run is in the index yet; every speed is an estimate from the memory-bandwidth model. Every Mac’s figure is in the table on this page with its provenance: published, community run or estimated.
Among Macs Apple sells new, the Mac Studio M5 Ultra (512 GB), $22,299 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with DeepSeek V3.2-Speciale, at ~18 tok/s (estimated).
No. On all 2 Mac configurations where DeepSeek V3.2-Speciale 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.
Q4_K_M (about 390 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 726 GB) is closer to full quality and needs more memory than any Mac has. Q3_K_M and Q2_K shrink it to about 336 and 233 GB at a quality cost. The index’s reference figure (18 tok/s on an M5 Ultra) is for its Q4_K_M build.
Its own window is 128K tokens. At macOS’s default GPU limit, the Mac Studio M5 Ultra (512 GB) holds about 128K (the full window).
LLMCheck. (2026). Can I run DeepSeek V3.2-Speciale on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/deepseek-v32-speciale/ (updated ). CC BY 4.0.