Home / Models / LFM2.5-2.6B

How to Run LFM2.5-2.6B Locally — Setup Guide (September 2026)

LFM2.5-2.6B is a genuinely small model built for edge hardware — 2.7B parameters, 1.7 GB on disk at Q4, and a convolutional backbone with attention on only 8 of its 30 layers. It is the model to reach for when the constraint is not "which quant fits my GPU" but "this has to run on a laptop with no discrete GPU at all".

Numbers you can trust

We don't print guessed speeds. Every measured number on this page came from TurboLLM's own auto-tuner running LFM2.5-2.6B on real hardware — labeled as such. When you run it yourself, TurboLLM benchmarks it on your exact GPU and shows a VRAM-fit verdict before you load, and the real measured tokens/sec once it's running.

Does it fit your GPU?

2.7B dense parameters on a hybrid stack: 22 short-convolution layers plus 8 full-attention layers, so the KV cache is a fraction of a conventional 3B model's. Native 131K context. Released under Liquid AI's own open licence rather than Apache or MIT.

LFM2.5-2.6B
Liquid AI · GGUF
Dense · convolution + attention hybrid
toolscode
VRAMFit
4 GB / CPU onlyQ4_K_M (1.7 GB) — runs on integrated graphics or plain CPU at usable speed · 131K context
8 GBQ8_0 (2.9 GB) fully in VRAM, near-lossless, with room to run an embedding model alongside it · 131K context
LiquidAI/LFM2.5-2.6B-GGUF
View on Hugging Face →

How to run it

  1. Install TurboLLM

    npx turbollm — no install step, works on Windows, macOS, and Linux. It detects your GPU and auto-provisions a matching llama-server build (no CUDA toolkit, no Python, no compiler).

  2. Get the model

    Paste LiquidAI/LFM2.5-2.6B-GGUF into TurboLLM's in-app Hugging Face search — it lists every quant with a VRAM-fit verdict against your real free VRAM, and downloads are resumable and SHA-256 verified.

  3. Let auto-fit pick the setup

    Flip the auto-fit toggle and TurboLLM chooses the GPU/CPU layer split (and, for a Mixture-of-Experts model, the expert-offload split) for your card — the same manual flag-hunting every other guide walks you through by hand.

  4. Load it

    TurboLLM benchmarks the model on your exact GPU as it loads and shows the real measured tokens/sec — not a number copied from someone else's card.

  5. Use it

    Chat in the built-in UI, or point any OpenAI- or Anthropic-compatible tool (including Claude Code) at TurboLLM's local API — see the API docs.

FAQ

Will LFM2.5-2.6B run on my GPU?

Check the VRAM table above for the tier closest to your card. If you're not sure which tier you're in, or want picks tailored to your exact hardware, use What can I run? — enter your VRAM (or Apple unified memory) and it suggests the model, quant, and offload split that fits, the same logic TurboLLM's auto-fit runs when you load a model.

Which quant should I use for LFM2.5-2.6B?

Pick the highest quant that fits your VRAM with room left over for the KV cache and compute buffer — not just the model weights. As a starting point, Q4_K_M is usually the sweet spot (small quality loss for a large size drop); step up to Q5_K_M/Q6_K/Q8_0 if you have headroom, or down to Q3_K_M/an IQ quant if you don't. TurboLLM shows a VRAM-fit verdict for every quant against your card's real free VRAM before you download — see Quantization explained for what the letters and numbers actually mean, or llama.cpp flags that actually matter for the other settings worth knowing.

How is running LFM2.5-2.6B on TurboLLM different from Ollama or LM Studio?

All three can run LFM2.5-2.6B as a GGUF. The differences show up around the edges: TurboLLM auto-tunes the quant and GPU/CPU split against your card's measured free VRAM rather than a fixed default, shows real generation speed instead of a guess, and lets you add a community fork — like the one behind this page, where relevant — without compiling anything yourself. Ollama and LM Studio each ship one blessed runtime you can't swap out. If your current setup already works well for you, there's no need to switch.

Run it now

$ npx turbollm

One command detects your GPU, provisions the right engine, and opens the UI. New here? Start with Install & first run and Quantization explained. On different hardware, see RTX 4060 or Apple M4 (16 GB). Also see how to run it or how to run it.