Yes: LFM2.5-2.6B runs on all 54 Macs in the LLMCheck index. It needs about 2 GB at a 4K context, 4 GB at 64K. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac mini M6 16 GB ($899; ~72 tok/s est.). Best measured figure: 220 tok/s on an M5 Max (published).
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 | Runs | Q4_K_M | estimated72 tok/s | 128K (full) | — |
| MacBook Air M5 24 GB | Runs | Q4_K_M | estimated72 tok/s | 128K (full) | — |
| MacBook Air M5 32 GB | Runs | Q4_K_M | estimated72 tok/s | 128K (full) | — |
| MacBook Air M1 8 GB refurb | Runs | Q4_K_M | estimated34 tok/s | 128K (full) | — |
| MacBook Air M4 16 GB used | Runs | Q4_K_M | estimated58 tok/s | 128K (full) | — |
| MacBook Air M2 16 GB refurb | Runs | Q4_K_M | estimated49 tok/s | 128K (full) | — |
| MacBook Air M3 16 GB refurb | Runs | Q4_K_M | estimated49 tok/s | 128K (full) | — |
| MacBook Air M1 16 GB refurb | Runs | Q4_K_M | estimated34 tok/s | 128K (full) | — |
| MacBook Air M4 24 GB used | Runs | Q4_K_M | estimated58 tok/s | 128K (full) | — |
| MacBook Air M2 24 GB refurb | Runs | Q4_K_M | estimated49 tok/s | 128K (full) | — |
| MacBook Air M3 24 GB refurb | Runs | Q4_K_M | estimated49 tok/s | 128K (full) | — |
| MacBook Pro | |||||
| MacBook Pro M6 16 GB | Runs | Q4_K_M | estimated72 tok/s | 128K (full) | M6 page |
| MacBook Pro M5 Pro 24 GB | Runs | 4-bit | sourced156 tok/s | 128K (full) | M5 Pro page |
| MacBook Pro M6 24 GB | Runs | Q4_K_M | estimated79 tok/s | 128K (full) | M6 page |
| MacBook Pro M6 32 GB | Runs | Q4_K_M | estimated79 tok/s | 128K (full) | M6 page |
| MacBook Pro M5 Pro 48 GB | Runs | 4-bit | sourced156 tok/s | 128K (full) | M5 Pro page |
| MacBook Pro M5 Max 64 GB | Runs | Q4_K_M | sourced220 tok/s | 128K (full) | M5 Max page |
| MacBook Pro M5 Pro 64 GB | Runs | 4-bit | sourced156 tok/s | 128K (full) | M5 Pro page |
| MacBook Pro M5 Max 128 GB | Runs | Q4_K_M | sourced220 tok/s | 128K (full) | M5 Max page |
| MacBook Pro M3 Max 64 GB refurb | Runs | Q4_K_M | estimated190 tok/s | 128K (full) | — |
| MacBook Pro M3 Max 128 GB refurb | Runs | Q4_K_M | estimated190 tok/s | 128K (full) | — |
| Mac mini | |||||
| Mac mini M6 16 GB | Runs | Q4_K_M | estimated72 tok/s | 128K (full) | M6 page |
| Mac mini M5 Pro 24 GB | Runs | 4-bit | sourced156 tok/s | 128K (full) | M5 Pro page |
| Mac mini M6 24 GB | Runs | Q4_K_M | estimated79 tok/s | 128K (full) | M6 page |
| Mac mini M6 32 GB | Runs | Q4_K_M | estimated79 tok/s | 128K (full) | M6 page |
| Mac mini M5 Pro 48 GB | Runs | 4-bit | sourced156 tok/s | 128K (full) | M5 Pro page |
| Mac mini M5 Pro 64 GB | Runs | 4-bit | sourced156 tok/s | 128K (full) | M5 Pro page |
| Mac mini M2 Pro 16 GB refurb | Runs | Q4_K_M | estimated91 tok/s | 128K (full) | — |
| Mac mini M4 16 GB used | Runs | Q4_K_M | estimated58 tok/s | 128K (full) | — |
| Mac mini M4 Pro 24 GB used | Runs | Q4_K_M | estimated142 tok/s | 128K (full) | — |
| Mac mini M4 24 GB used | Runs | Q4_K_M | estimated58 tok/s | 128K (full) | — |
| Mac mini M2 Pro 32 GB refurb | Runs | Q4_K_M | estimated91 tok/s | 128K (full) | — |
| Mac mini M4 Pro 48 GB used | Runs | Q4_K_M | estimated142 tok/s | 128K (full) | — |
| Mac mini M4 Pro 64 GB used | Runs | Q4_K_M | estimated142 tok/s | 128K (full) | — |
| iMac | |||||
| iMac M6 16 GB | Runs | Q4_K_M | estimated72 tok/s | 128K (full) | M6 page |
| iMac M6 24 GB | Runs | Q4_K_M | estimated79 tok/s | 128K (full) | M6 page |
| iMac M6 32 GB | Runs | Q4_K_M | estimated79 tok/s | 128K (full) | M6 page |
| Mac Studio | |||||
| Mac Studio M5 Max 36 GB | Runs | Q4_K_M | estimated203 tok/s | 128K (full) | M5 Max page |
| Mac Studio M5 Max 48 GB | Runs | Q4_K_M | sourced220 tok/s | 128K (full) | M5 Max page |
| Mac Studio M5 Max 64 GB | Runs | Q4_K_M | sourced220 tok/s | 128K (full) | M5 Max page |
| Mac Studio M5 Ultra 96 GB | Runs | Q4_K_M | estimated333 tok/s | 128K (full) | — |
| Mac Studio M5 Max 128 GB | Runs | Q4_K_M | sourced220 tok/s | 128K (full) | M5 Max page |
| Mac Studio M5 Ultra 256 GB | Runs | Q4_K_M | estimated333 tok/s | 128K (full) | — |
| Mac Studio M5 Ultra 512 GB | Runs | Q4_K_M | estimated333 tok/s | 128K (full) | — |
| Mac Studio M2 Max 32 GB refurb | Runs | Q4_K_M | estimated190 tok/s | 128K (full) | — |
| Mac Studio M1 Ultra 64 GB refurb | Runs | Q4_K_M | estimated261 tok/s | 128K (full) | — |
| Mac Studio M4 Max 64 GB used | Runs | Q4_K_M | estimated203 tok/s | 128K (full) | M4 Max page |
| Mac Studio M2 Max 64 GB refurb | Runs | Q4_K_M | estimated190 tok/s | 128K (full) | — |
| Mac Studio M1 Ultra 128 GB refurb | Runs | Q4_K_M | estimated261 tok/s | 128K (full) | — |
| Mac Studio M2 Ultra 128 GB refurb | Runs | Q4_K_M | estimated261 tok/s | 128K (full) | — |
| Mac Studio M4 Max 128 GB used | Runs | Q4_K_M | estimated203 tok/s | 128K (full) | M4 Max page |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated261 tok/s | 128K (full) | — |
| Mac Studio M3 Ultra 256 GB used | Runs | Q4_K_M | estimated265 tok/s | 128K (full) | — |
| Mac Studio M3 Ultra 512 GB refurb | Runs | Q4_K_M | estimated265 tok/s | 128K (full) | — |
Context memory is computed from its config.json (hybrid short-conv: attention on 8 of 30 layers; conv layers keep a constant state): about 1.1 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.
macOS lets the GPU use only part of unified memory by default. LFM2.5-2.6B 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 2.6B 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 2 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 | — | 2 GB | 2 GB | 3 GB | 16 GB |
| Q2_K | 0.9 GB | 3 GB | 3 GB | 4 GB | 16 GB |
| Q3_K_M | 1.3 GB | 3 GB | 4 GB | 4 GB | 16 GB |
| Q4_K_M | 1.5 GB | 3 GB | 4 GB | 4 GB | 16 GB |
| Q5_K_M | 1.8 GB | 4 GB | 4 GB | 5 GB | 16 GB |
| Q6_K | 2.1 GB | 4 GB | 5 GB | 5 GB | 16 GB |
| Q8_0 | 2.8 GB | 5 GB | 5 GB | 6 GB | 16 GB |
| F16 | 5.2 GB | 7 GB | 8 GB | 8 GB | 16 GB |
Every published (filled square) and community (hollow circle) run the index holds for LFM2.5-2.6B: 3 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.
| Chip | Runtime | Quant | Decode | Context | Date | Source |
|---|---|---|---|---|---|---|
| M5 Max | MLX | Q4_K_M | sourced220 tok/s | — | 2026-08 | liquid.ai |
| M4 Max | llama.cpp | FP16 | sourced61 tok/s | batch 1, temperature 0, up to 256 generated | 2026-08-20 | liquid.ai not an anchor |
| M5 Pro | MLX | 4-bit | sourced156.16 tok/s | decode at 4K context depth | 2026-10-19 | huggingface.co |
The index has no verified Ollama tag for LFM2.5-2.6B. 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 mini M6 (16 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~72 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 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), ~72 tok/s (estimated).
As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence the verdicts.
Yes. LFM2.5-2.6B needs about 2 GB of unified memory at a short (4K-token) context, so it runs on 54 of the 54 Mac configurations in the LLMCheck index. The smallest Mac Apple sells new that runs it is the Mac mini M6 (16 GB).
About 2 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 3 GB in total at 32K and 4 GB at 64K with the default 16-bit cache (about 3 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 220 tok/s (published figure) at Q4_K_M. The best measured figure is 220 tok/s on an M5 Max 64 GB (published figure, Q4_K_M). 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 mini M6 (16 GB), $899 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with LFM2.5-2.6B, at ~72 tok/s (estimated).
No. On all 54 Mac configurations where LFM2.5-2.6B 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 1 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 3 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 1 and 1 GB at a quality cost. The index’s reference figure (220 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 M6 (16 GB) holds about 128K (the full window).
LLMCheck. (2026). Can I run LFM2.5-2.6B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/lfm25-26b/ (updated ). CC BY 4.0.