LFM2.5-24B-A2B is a 24B-parameter reasoning model with only 2B active parameters, built for fast, private agents on-device. It is the largest and final model in the LFM2.5 family, which now spans two orders of magnitude: from LFM2.5-230M to LFM2.5-24B-A2B.
Best-in-class agent: Competitive with Qwen3.6-35B-A3B, a model with ~50% more total and active parameters, on agentic and tool-use tasks, scoring 48.09 on LiveClaw versus 38.19.
Reasoning at MoE speed: Always thinks before it answers. With only 2B active parameters per token, each reasoning token is cheap.
Efficient inference: Runs up to 1.7× faster than comparable MoEs on-device, with 184 tok/s on an Apple M5 Max and up to 21K output tok/s on a single NVIDIA B300 GPU.
Find more information about LFM2.5-24B-A2B in our blog post.
MLX format for Apple Silicon. Optimized for fast inference on Mac devices using the MLX framework.
LFM2.5-24B-A2B-DSpark
DSpark draft model for speculative decoding with SGLang, for faster generation. Coming soon.
We recommend using it for agents that need to reason, call tools, and run reliably on your device. It is not recommended for knowledge-heavy tasks on its own: pair it with retrieval or web search, which plays to its tool-calling strength.
<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
What is C. elegans?<|im_end|>
<|im_start|>assistant
<think>
Tip. 💡 Note: Unlike LFM2-24B-A2B, LFM2.5-24B-A2B is a pure reasoning model that always thinks before it answers. It adds a <think> tag directly in the chat template when starting an assistant answer.
Function definition: Provide the list of tools as a JSON object in the system prompt, or use tokenizer.apply_chat_template() with tools=....
Function call: By default, LFM2.5 writes Pythonic function calls (a Python list between <|tool_call_start|> and <|tool_call_end|> special tokens), as the assistant answer. You can override this behavior by asking the model to output JSON function calls in the system prompt.
Function execution: Execute the call and return the result with the tool role.
Final answer: LFM2.5 interprets the tool output and returns a plain-text answer addressing the original prompt.
<|startoftext|><|im_start|>system
List of tools: [{"name": "get_candidate_status", "description": "Retrieves the current status of a candidate in the recruitment process", "parameters": {"type": "object", "properties": {"candidate_id": {"type": "string", "description": "Unique identifier for the candidate"}}, "required": ["candidate_id"]}}]<|im_end|>
<|im_start|>user
What is the current status of candidate ID 12345?<|im_end|>
<|im_start|>assistant
<|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
<|im_start|>tool
[{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}]<|im_end|>
<|im_start|>assistant
The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>
LFM2.5-24B-A2B keeps the LFM2-24B-A2B architecture with two changes: the context window grows from 32K to 131K tokens, and the vocabulary doubles from 65K to 128K tokens through an in-place tokenizer expansion for better non-Latin tokenization.
Pre-training: ~33T tokens, up from ~17T.
Mid-training: 2T tokens at 32K context on curated, higher-quality data weighted toward reasoning, math, code, instruction following, and multilingual text, then 300B tokens of long-context data at 131K context. Tool calls and multi-turn trajectories appear in both phases.
Post-training: supervised fine-tuning, teacher specialization, two multi-domain on-policy distillation stages (one non-agentic, one agentic), and agentic reinforcement learning inside popular agent harnesses (OpenClaw, Hermes Agent, Pi, OpenCode), so the model learns their tools, system prompts, and interaction patterns.
All the models were evaluated with vLLM and the following generation parameters:
AutomationBench: temperature = 0.6, top_p = 0.95, max_turns = 50, no max output tokens (bounded by the model's context window).
BFCLv4: temperature = 0.001, max output tokens = 4096.
ToolSandbox: temperature = 0, max output tokens = 1024; user simulator: GPT-4o-2024-08-06, temperature = 0, max output tokens = 1024.
LiveClaw: temperature = 1.0 (vLLM default; the agent sets no temperature), max output tokens = 8192.
τ³-Bench Banking: official user model (GPT-5.2, low reasoning effort) with default BM25 retrieval, temperature = 0, max output tokens = 16384 per turn.
WebArena Verified: temperature = 0.6, top_p = 0.95, max_turns = 40 (number of browser actions allowed), no max output tokens (bounded by the model's context window).
Other evals: temperature = 0.6, max output tokens = 32768.
LFM2.5-24B-A2B is the fastest of the compared MoEs at reading in prompts and generating answers. It decodes 184 tokens/s on an Apple M5 Max and 114 tokens/s on an AMD Ryzen AI Max+ 395, up to 1.7x faster than the next-best model, while using the least memory.
We measure GPU throughput (total output tokens / wall time) on a single NVIDIA B300 GPU with SGLang 0.5.22, using 1,024 input tokens, up to 256 output tokens, and BF16 weights. At each concurrency level, we continuously maintain the target number of in-flight requests, replacing each completed request immediately.
@article{liquidAI202624BA2B,
author = {Liquid AI},
title = {LFM2.5-24B-A2B: Built for Fast On-Device Agents},
journal = {Liquid AI Blog},
year = {2026},
note = {www.liquid.ai/blog/lfm2-5-24b-a2b},
}
@article{liquidai2025lfm2,
title = {LFM2 Technical Report},
author = {Liquid AI},
journal = {arXiv preprint arXiv:2511.23404},
year = {2025}
}
Files
13 files · 171 GBWeights 7.47 GB (smallest of 10 GGUF variants). Sizes and sha256 from the signed manifest.
# custom terms: read the license before you download$ fw get unsloth/LFM2.5-24B-A2B-GGUF
# manifest sha256 7ad65930e0d2… · 171 GB · 13 files$ fw verify ./LFM2.5-24B-A2B-GGUF unsloth/LFM2.5-24B-A2B-GGUF
Terms that come with these files. LFM 1.0: commercial use only for organisations under US$10M annual revenue. Keep a copy of the license with the files.
Custom license (custom).Read the license text first. Open this panel to show the commands once you accept its terms.
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.lfmSubject: 
