Ollama · lfm2.5

![image.png](/assets/library/lfm2.5-thinking/0f3b101a-f2ef-4a5c-a0bb-a8edecac35e3) LFM2.5 is a family of hybrid models from Liquid AI designed for on-device deployment. It builds on the LFM2 architec…

ollama/lfm2.5

![image.png](/assets/library/lfm2.5-thinking/0f3b101a-f2ef-4a5c-a0bb-a8edecac35e3)

LFM2.5 is a family of hybrid models from Liquid AI designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

### LFM2.5-24B-A2B

The largest and final model in the LFM2.5 family: a 24B reasoning model that activates only about 2B parameters per token, built for fast, private agents on your own hardware.

``` ollama run lfm2.5:24b ```

- **Built for agents**: Trained with reinforcement learning inside popular agent harnesses. Liquid AI reports a LiveClaw score of 48.09, ahead of Qwen3.6-35B-A3B (38.19), a model with about 50% more parameters. - **Always reasons**: Thinks before every answer, and with only 2B active parameters each reasoning token is cheap. - **Long context**: 128K tokens. - **Multilingual**: English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian and Polish.

Use it for agents that reason and call tools. For knowledge-heavy questions, pair it with web search or retrieval.

### Use it with your agent

Liquid AI trained LFM2.5-24B-A2B inside OpenClaw, Hermes Agent, Pi and OpenCode. Start any of them with Ollama:

``` ollama launch opencode --model lfm2.5:24b ```

``` ollama launch hermes --model lfm2.5:24b ```

### LFM2.5-8B-A1B

An edge model built for fast, reliable tool calling on consumer hardware.

``` ollama run lfm2.5:8b ```

- **On-device personal assistant**: Designed to power real-life applications, chaining tool calls, and following complex instructions on all devices. - **Compressed performance**: Competitive with much larger dense and MoE models on instruction following and agentic tasks. - **Unmatched throughput**: Fastest in its size class on both CPU and GPU inference

![benchmark](/assets/library/lfm2.5/2eecda91-5cc6-4212-9382-25e05b6e68ad)

Specifications & capabilities

Published model ID
lfm2.5

Deployments & artifacts

1–10 / 10

ollama

source id
ollama
execution mode
local
parameter size
24.0B
parameter count
24000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
14526269093
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
24.0B
parameter count
24000000000
parameter count is approximate
true
quantization level
BF16
context window
128000
context window is approximate
true
artifact size bytes
47962105509
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
24.0B
parameter count
24000000000
parameter count is approximate
true
quantization level
Q4_0
context window
128000
context window is approximate
true
artifact size bytes
13578201509
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
24.0B
parameter count
24000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
14526269093
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
24.0B
parameter count
24000000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
25493743269
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.5B
parameter count
8500000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
125000
context window is approximate
true
artifact size bytes
5156075045
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.5B
parameter count
8500000000
parameter count is approximate
true
quantization level
F16
context window
125000
context window is approximate
true
artifact size bytes
16947770917
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.5B
parameter count
8500000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
125000
context window is approximate
true
artifact size bytes
5156075045
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.5B
parameter count
8500000000
parameter count is approximate
true
quantization level
Q8_0
context window
125000
context window is approximate
true
artifact size bytes
9010705957
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.5B
parameter count
8500000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
125000
context window is approximate
true
artifact size bytes
5156075045
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace