Yes: Hermes 4 70B runs on 25 of the 54 Macs in the LLMCheck index. It needs about 38 GB at a 4K context, 59 GB at 64K. Smallest current Mac: the Mac mini M5 Pro 48 GB, raised GPU limit; cheapest at 15+ tok/s: the Mac Studio M5 Ultra 96 GB ($5,499; ~24 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 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).
| 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 | Raise GPU limit command ↓ | Q4_K_M | estimated6 tok/s | — | |
| MacBook Pro M5 Max 64 GB | Runs, slowly | Q4_K_M | estimated12 tok/s | 45K | — |
| MacBook Pro M5 Pro 64 GB | Runs, slowly | Q4_K_M | estimated6 tok/s | 45K | — |
| MacBook Pro M5 Max 128 GB | Runs, slowly | Q4_K_M | estimated12 tok/s | 128K (full) | — |
| MacBook Pro M3 Max 64 GB refurb | Runs, slowly | Q4_K_M | estimated8 tok/s | 33K | — |
| MacBook Pro M3 Max 128 GB refurb | Runs, slowly | Q4_K_M | estimated8 tok/s | 128K (full) | — |
| 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 | Raise GPU limit command ↓ | Q4_K_M | estimated6 tok/s | — | |
| Mac mini M5 Pro 64 GB | Runs, slowly | Q4_K_M | estimated6 tok/s | 45K | — |
| 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 | Raise GPU limit command ↓ | Q4_K_M | estimated6 tok/s | — | |
| Mac mini M4 Pro 64 GB used | Runs, slowly | Q4_K_M | estimated6 tok/s | 33K | — |
| 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 | Raise GPU limit command ↓ | Q4_K_M | estimated12 tok/s | — | |
| Mac Studio M5 Max 64 GB | Runs, slowly | Q4_K_M | estimated12 tok/s | 45K | — |
| Mac Studio M5 Ultra 96 GB | Runs | Q4_K_M | estimated24 tok/s | 122K | — |
| Mac Studio M5 Max 128 GB | Runs, slowly | Q4_K_M | estimated12 tok/s | 128K (full) | — |
| Mac Studio M5 Ultra 256 GB | Runs | Q4_K_M | estimated24 tok/s | 128K (full) | — |
| Mac Studio M5 Ultra 512 GB | Runs | Q4_K_M | estimated24 tok/s | 128K (full) | — |
| Mac Studio M2 Max 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 64 GB refurb | Runs | Q4_K_M | estimated16 tok/s | 33K | — |
| Mac Studio M4 Max 64 GB used | Runs, slowly | Q4_K_M | estimated11 tok/s | 33K | — |
| Mac Studio M2 Max 64 GB refurb | Runs, slowly | Q4_K_M | estimated8 tok/s | 33K | — |
| Mac Studio M1 Ultra 128 GB refurb | Runs | Q4_K_M | estimated16 tok/s | 128K (full) | — |
| Mac Studio M2 Ultra 128 GB refurb | Runs | Q4_K_M | estimated16 tok/s | 128K (full) | — |
| Mac Studio M4 Max 128 GB used | Runs, slowly | Q4_K_M | estimated11 tok/s | 128K (full) | — |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated16 tok/s | 128K (full) | — |
| Mac Studio M3 Ultra 256 GB used | Runs | Q4_K_M | estimated16 tok/s | 128K (full) | — |
| Mac Studio M3 Ultra 512 GB refurb | Runs | Q4_K_M | estimated16 tok/s | 128K (full) | — |
Context memory is computed from its config.json (GQA on all 80 layers (8 kv heads x 128)): about 21.5 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 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 Hermes 4 70B needs about 38 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.
sudo sysctl iogpu.wired_limit_mb=43008sudo sysctl iogpu.wired_limit_mb=43008Weights are 70B 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 38 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 | — | 38 GB | 47 GB | 58 GB | 64 GB |
| Q2_K | 23.8 GB | 26 GB | 35 GB | 46 GB | 36 GB |
| Q3_K_M | 34.3 GB | 36 GB | 46 GB | 56 GB | 48 GB |
| Q4_K_M | 39.9 GB | 42 GB | 51 GB | 62 GB | 64 GB |
| Q5_K_M | 49.7 GB | 52 GB | 61 GB | 72 GB | 64 GB |
| Q6_K | 57.4 GB | 59 GB | 69 GB | 80 GB | 96 GB |
| Q8_0 | 74.2 GB | 76 GB | 86 GB | 96 GB | 96 GB |
| F16 | 140.0 GB | 142 GB | 151 GB | 162 GB | 256 GB |
The index holds no published or community run of Hermes 4 70B 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 Hermes 4 70B. Start from its listing and copy the exact name of a build that fits: Hugging Face repo → · model card →
GGUF builds run in LM Studio or llama.cpp; MLX builds run in LM Studio or mlx-lm.
On the Mac mini M5 Pro (64 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~6 tok/s (estimated) at Q4_K_M; keep the context at or under 45K there, or use a q8 KV cache.
Step-by-step: the Ollama install guide.
Mac mini M5 Pro (48 GB) — smallest current Mac that runs it, $2,299 new (Apple list price, checked 2026-11-14), ~6 tok/s (estimated) once the GPU memory limit is raised. Mac Studio M5 Ultra (96 GB) — cheapest at 15+ tok/s, $5,499 new (Apple list price, checked 2026-11-14), ~24 tok/s (estimated). Amazon does not stock the Mac mini M5 Pro (48 GB): Apple builds it to order. Amazon does not stock the Mac Studio M5 Ultra (96 GB): Apple builds it to order.
Yes. Hermes 4 70B needs about 38 GB of unified memory at a short (4K-token) context, so it runs on 25 of the 54 Mac configurations in the LLMCheck index; 21 of them hold it inside macOS’s default GPU memory limit and 4 only after raising that limit. The smallest Mac Apple sells new that runs it is the Mac mini M5 Pro (48 GB).
About 38 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 48 GB in total at 32K and 59 GB at 64K with the default 16-bit cache (about 49 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.
On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~12 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 (96 GB), $5,499 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Hermes 4 70B, at ~24 tok/s (estimated).
On 4 of the 54 configurations, yes: Mac mini M5 Pro 48 GB, Mac Studio M5 Max 48 GB, MacBook Pro M5 Pro 48 GB and 1 more. macOS lets the GPU use only part of unified memory by default (about 37 GB on the Mac mini M5 Pro (48 GB)), and Hermes 4 70B needs about 38 GB. Running sudo sysctl iogpu.wired_limit_mb=43008 in Terminal raises the limit on a 48 GB Mac until the next restart. From 64 GB up, every Mac Apple sells new holds it inside the default limit.
Q4_K_M (about 40 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 74 GB) is closer to full quality and needs a 96 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 34 and 24 GB at a quality cost. The index’s reference figure (12 tok/s on an M5 Max) is for its Q4_K_M build.
Its own window is 128K tokens. At macOS’s default GPU limit, the Mac mini M5 Pro (64 GB) holds about 45K. The full window needs about 80 GB, which a 128 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.
LLMCheck. (2026). Can I run Hermes 4 70B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/hermes-4-70b/ (updated ). CC BY 4.0.