LFM2.5 Thinking

What LFM2.5 Thinking is for

LFM2.5 Thinking is a reasoning model: it spends output tokens working through a problem before answering, which makes it slower per useful word and better on problems that need the working shown. Liquid AI released it in 2026-01 with a single 1.2B size under Apache 2.0, with a 32K context window. Budget for the extra tokens the thinking phase consumes. The catalogue records its strength as small reasoning model on edge hardware.

Sizes and memory

The 1.2B needs about 1 GB of weights at Q4_K_M. That is the whole range; there is no larger or smaller variant in this record. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.

Size	Weights at Q4_K_M	Recommended VRAM	Smallest card in our guide that holds it
1.2B	1 GB	2 GB	NVIDIA Jetson Orin Nano 8GB

Hardware that runs LFM2.5 Thinking

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of LFM2.5 Thinking at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 1.2B.

The largest size any of them holds is the 1.2B at 1 GB, on the NVIDIA Jetson Orin Nano 8GB (8 GB at 68 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.

What people use it for

The catalogue lists 4 recorded uses for LFM2.5 Thinking: edge, reasoning, small chat, mobile. It is tagged reasoning, thinking, edge, small.

Where LFM2.5 Thinking sits in the LFM2 family

LFM2.5 Thinking is the only LFM2 entry in our catalogue, so there is no in-family alternative to weigh it against; the comparison to make is against the models listed at the foot of this page.

The Apache 2.0 licence puts no usage ceiling on it, which matters if the thing you are building has users. That is the practical difference between this and a vendor community licence.

Context window: 32K

32K tokens is about 24,000 words at the usual ratio — enough for a handful of files or a long report held whole. It is the point at which the KV cache starts to be a serious share of memory: doubling the context you actually use costs roughly double the cache, on top of the 1 GB of weights.

How to run LFM2.5 Thinking locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for LFM2.5 Thinking at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "LFM2.5 Thinking GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.