Can I run it?
Can I run LFM2.5 2.6B on Apple M1 Max?
Runs great
Runs great fully in unified memory on your Apple M1 Max at BF16, 8K context, about 37–51 tok/s. Weights 5.03 GB plus 0.47 GB of KV cache — 5.85 GB of 24.0 GB usable. Up to 128K context still fits.
Best quantBF16
Working context8K
Max that fits128K
Speed37–51 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights5.03 GB
KV cache0.47 GB
Total5.85 GB
Usable24.0 GB
LFM2.5 2.6B details · Apple M1 Max page · How this estimate is made
Run commands
llama.cpp
llama-server -hf LiquidAI/LFM2.5-2.6B-GGUF:BF16 -c 8192 -ngl 30
Ollama
ollama run lfm2.5
LM Studio
lms get LiquidAI/LFM2.5-2.6B-GGUF # Then load quant BF16
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- BF16 size is the real GGUF file size from Hugging Face.
- Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.8 27B on Apple M1 Max? — Tight fit, UD-Q6_K_L, 9.0–12 tok/s (estimate)
- Can I run gemma 4 12b it on Apple M1 Max? — Tight fit, BF16, 8.6–12 tok/s (estimate)
- Can I run Qwen3.5 9B on Apple M1 Max? — Runs, BF16, 12–16 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.