Yes: Step-3.7-Flash runs on 12 of 54 Macs in the LLMCheck index. It needs about 65 GB at a 4K context, 69 GB at 64K. Smallest current Mac: the Mac Studio M5 Ultra 96 GB; cheapest at 15+ tok/s: the Mac Studio M5 Max 128 GB ($5,099; 48 tok/s community-measured). Best measured figure: 68.5 tok/s on an M5 Ultra (community).
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 | Runs | oQ2e | community48 tok/s | 256K (full) | M5 Max page |
| MacBook Pro M3 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro M3 Max 128 GB refurb | Runs | Q4_K_M | estimated20 tok/s | 256K (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 | 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 | Runs | 2.7 bpw | estimated69 tok/s | 256K (full) | M5 Ultra page |
| Mac Studio M5 Max 128 GB | Runs | oQ2e | community48 tok/s | 256K (full) | M5 Max page |
| Mac Studio M5 Ultra 256 GB | Runs | 4-bit | community69 tok/s | 256K (full) | M5 Ultra page |
| Mac Studio M5 Ultra 512 GB | Runs | 4-bit | community69 tok/s | 256K (full) | M5 Ultra page |
| 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 | Runs | Q4_K_M | estimated56 tok/s | 256K (full) | — |
| Mac Studio M2 Ultra 128 GB refurb | Runs | Q4_K_M | estimated56 tok/s | 256K (full) | — |
| Mac Studio M4 Max 128 GB used | Runs | Q4_K_M | estimated26 tok/s | 256K (full) | M4 Max page |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated56 tok/s | 256K (full) | — |
| Mac Studio M3 Ultra 256 GB used | Runs | 4-bit | community57 tok/s | 256K (full) | M3 Ultra page |
| Mac Studio M3 Ultra 512 GB refurb | Runs | 4-bit | community57 tok/s | 256K (full) | M3 Ultra page |
Context memory is computed from its config.json (12 full layers + 33 sliding-window layers (window 512)): about 3.3 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.
macOS lets the GPU use only part of unified memory by default. Step-3.7-Flash 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 198B 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 198B parameters sit in memory although only 11B are read per token. The first row is the catalog’s own figure (about 65 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 | — | 65 GB | 66 GB | 68 GB | 96 GB |
| Q2_K | 67.3 GB | 69 GB | 71 GB | 72 GB | 96 GB |
| Q3_K_M | 97.0 GB | 99 GB | 100 GB | 102 GB | 128 GB |
| Q4_K_M | 112.9 GB | 115 GB | 116 GB | 118 GB | 256 GB |
| Q5_K_M | 140.6 GB | 143 GB | 144 GB | 146 GB | 256 GB |
| Q6_K | 162.4 GB | 164 GB | 166 GB | 167 GB | 256 GB |
| Q8_0 | 209.9 GB | 212 GB | 213 GB | 215 GB | 256 GB |
| F16 | 396.0 GB | 398 GB | 399 GB | 401 GB | 512 GB |
Every published (filled square) and community (hollow circle) run the index holds for Step-3.7-Flash: 2 published, 4 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.
| Chip | Runtime | Quant | Decode | Context | Date | Source |
|---|---|---|---|---|---|---|
| M5 Ultra | MLX | 4-bit | community68.5 tok/s | 1k | 2026-10-19 | omlx.ai |
| M3 Ultra | MLX | 4-bit | community57 tok/s | 1k | 2026-08-24 | omlx.ai |
| M5 Max | MLX | oQ3e | community51.3 tok/s | 1k | 2026-08-16 | omlx.ai |
| M5 Max | MLX | oQ2e | community48.2 tok/s | 1k | 2026-08-24 | omlx.ai |
| M4 Max | llama.cpp | Q4_K_S | sourced51.2 tok/s | TG128 from an empty prompt | 2026-05-28 | huggingface.co not an anchor |
| M4 Max | llama.cpp | IQ4_XS | sourced49.58 tok/s | TG128 from an empty prompt | 2026-05-28 | huggingface.co not an anchor |
The index has no verified Ollama tag for Step-3.7-Flash. 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 Studio M5 Ultra (96 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~69 tok/s (estimated) at 2.7 bpw; keep the context at or under 256K there, or use a q8 KV cache.
Step-by-step: the Ollama install guide.
Mac Studio M5 Ultra (96 GB) — smallest current Mac that runs it, $5,499 new (Apple list price, checked 2026-11-14), ~69 tok/s (estimated). Mac Studio M5 Max (128 GB) — cheapest at 15+ tok/s, $5,099 new (Apple list price, checked 2026-11-14), 48 tok/s (community run). Amazon does not stock the Mac Studio M5 Ultra (96 GB): Apple builds it to order. Amazon does not stock the Mac Studio M5 Max (128 GB): Apple builds it to order.
Yes. Step-3.7-Flash needs about 65 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).
About 65 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 67 GB in total at 32K and 69 GB at 64K with the default 16-bit cache (about 67 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 48 tok/s (community run) at oQ2e. The best measured figure is 68.5 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.
Among Macs Apple sells new, the Mac Studio M5 Max (128 GB), $5,099 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Step-3.7-Flash, at 48 tok/s (community run).
No. On all 12 Mac configurations where Step-3.7-Flash 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 113 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 210 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 97 and 67 GB at a quality cost. The index’s reference figure (48 tok/s on an M5 Max) is for its oQ2e build.
Its own window is 256K tokens. At macOS’s default GPU limit, the Mac Studio M5 Ultra (96 GB) holds about 256K (the full window).
LLMCheck. (2026). Can I run Step-3.7-Flash on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/step-37-flash/ (updated ). CC BY 4.0.