The LLMCheck index estimates LFM2.5-2.6B at ~203 tok/s on an M4 Max at Q4_K_M, a figure from its published bandwidth model, not a measured run. It needs about 2 GB of unified memory. It is Liquid AI's 2.6B dense model, released under the LFM Open licence.
Want to run LFM2.5-2.6B faster — or step up to bigger models? Find your Mac →This is an LLMCheck index estimate from its published two-term bandwidth model, not a measured run; the index labels it so everywhere it appears. Own this Mac? Submit a real run →
| Metric | Value |
|---|---|
| Tokens per second | estimated~203 tok/s |
| Provenance | estimate · how estimates are made |
| Quantization | Q4_K_M |
| Minimum RAM | 2 GB |
| Parameters | 2.6B |
| Chip bandwidth | 546 GB/s |
Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (2 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| sourced61 tok/s | FP16 | llama.cpp | — | batch 1, temperature 0, up to 256 generated | liquid.ai | Liquid AI's DSpark post: target-only decode on an M4 Max MacBook Pro, mean of five prompt sets (60–62), llama.cpp with Metal kernels from then-unmerged PRs #27383 / #27441, so it does not anchor. The 139 tok/s with the DSpark drafter is speculative decoding, not this row.; not used to anchor estimates |
Ollama — the index has not verified an Ollama tag for LFM2.5-2.6B, so it doesn’t print one (a guessed tag fails with “pull model manifest: file does not exist”). Search the Ollama library →
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Search the Ollama library → · model card →
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
Liquid AI's 2.6B model, ~220 tok/s on M5 Max. LFM Open license, LLMCheck capability 14/50.
LFM Open licence · 2.6B · 131K context · LLMCheck capability 14/50 · see its leaderboard rank →
LFM2.5-2.6B needs about 2 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how LFM2.5-2.6B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard