Total runs:
1.1M
Run Growth:
894.0K
Growth Rate:
81.41%
Sponsored by
APIMart
LiquidAI / LFM2.5-8B-A1B-Base
Model's Last Updated: May 29 2026
text-generation
Introduction of LFM2.5-8B-A1B-Base
Model Details of LFM2.5-8B-A1B-Base
LFM2.5-8B-A1B-Base
LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
- 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, with day-one support for llama.cpp, MLX, vLLM, and SGLang.
Find more information about LFM2.5-8B-A1B in our blog post .
* AA-Omniscience Index (higher is better) rewards correct answers and penalizes hallucinations. Scores range from -100 to 100. See more results on Artificial Analysis .
🗒️ Model Details
| Model | Parameters | Description |
|---|---|---|
| LFM2.5-8B-A1B-Base | 8.3B total / 1.5B active | Pre-trained base model for fine-tuning |
| LFM2.5-8B-A1B | 8.3B total / 1.5B active | Reasoning-tuned general-purpose model |
LFM2.5-8B-A1B is a general-purpose text-only model with the following features:
- Total parameters : 8.3B
- Active parameters : 1.5B
- Number of layers : 24 (18 double-gated LIV conv + 6 GQA)
- Training budget : 38 trillion tokens
- Context length : 131,072
- Vocabulary size : 128,000
- Languages : English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, Spanish
-
Generation parameters
: We recommend the following parameters:
-
temperature: 0.2 -
top_p: 80 -
repetition_penalty: 1.05
-
| Model | Description |
|---|---|
| LFM2.5-8B-A1B | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers, vLLM, and SGLang. |
| LFM2.5-8B-A1B-GGUF | Quantized format for llama.cpp and compatible tools. Optimized for edge inference and local deployment. |
| LFM2.5-8B-A1B-ONNX | ONNX Runtime format for cross-platform deployment. |
| LFM2.5-8B-A1B-MLX | MLX format for Apple Silicon. Optimized for fast inference on Mac devices. |
We recommend using LFM2.5-8B-A1B for agentic workflows, tool use, structured outputs, multilingual assistants, and on-device personal-assistant applications. It is not the best fit for heavy programming or knowledge-intensive question answering without retrieval.
🏃 Inference
LFM2.5-8B-A1B is supported by many inference frameworks. See the Inference documentation for the full list.
| Name | Description | Docs | Notebook |
|---|---|---|---|
| Transformers | Simple inference with direct access to model internals. | Link |
|
| vLLM | High-throughput production deployments with GPU. | Link |
|
| llama.cpp | Cross-platform inference with CPU offloading. | Link |
|
| MLX | Apple's machine learning framework optimized for Apple Silicon. | Link | — |
| LM Studio | Desktop application for running LLMs locally. | Link | — |
Quick start with Transformers (compatible with
transformers>=5.0.0
):
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model_id = "LiquidAI/LFM2.5-8B-A1B-Base"
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
dtype="bfloat16",
# attn_implementation="flash_attention_2" <- uncomment on compatible GPU
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
prompt = "What is C. elegans?"
input_ids = tokenizer.apply_chat_template(
[{"role": "user", "content": prompt}],
add_generation_prompt=True,
return_tensors="pt",
tokenize=True,
).to(model.device)
output = model.generate(
input_ids,
do_sample=True,
temperature=0.2,
top_k=80,
repetition_penalty=1.05,
max_new_tokens=8192,
streamer=streamer,
)
🔧 Fine-Tuning
We recommend fine-tuning LFM2.5 for your specific use case to achieve the best results.
| Name | Description | Docs | Notebook |
|---|---|---|---|
| CPT ( Unsloth ) | Continued Pre-Training using Unsloth for text completion. | Link |
|
| CPT ( Unsloth ) | Continued Pre-Training using Unsloth for translation. | Link |
|
| SFT ( Unsloth ) | Supervised Fine-Tuning with LoRA using Unsloth. | Link |
|
| SFT ( TRL ) | Supervised Fine-Tuning with LoRA using TRL. | Link |
|
| DPO ( TRL ) | Direct Preference Optimization with LoRA using TRL. | Link |
|
| GRPO ( Unsloth ) | GRPO with LoRA using Unsloth. | Link |
|
| GRPO ( TRL ) | GRPO with LoRA using TRL. | Link |
|
📬 Contact
- Got questions or want to connect? Join our Discord community .
- If you are interested in custom solutions with edge deployment, please contact our sales team .
Citation
@article{liquidAI20268BA1B,
author = {Liquid AI},
title = {LFM2.5-8B-A1B: Personal Assistant On Your Laptop},
journal = {Liquid AI Blog},
year = {2026},
note = {www.liquid.ai/blog/lfm2-5-8b-a1b},
}
@article{liquidai2025lfm2,
title = {LFM2 Technical Report},
author = {Liquid AI},
journal = {arXiv preprint arXiv:2511.23404},
year = {2025}
}
Runs of LiquidAI LFM2.5-8B-A1B-Base on huggingface.co
1.8K
Total runs
0
24-hour runs
43
3-day runs
-501
7-day runs
-2.2K
30-day runs
More Information About LFM2.5-8B-A1B-Base huggingface.co Model
Url of LFM2.5-8B-A1B-Base
LFM2.5-8B-A1B-Base huggingface.co Url
Provider of LFM2.5-8B-A1B-Base huggingface.co
Other API from LiquidAI
Updated:August 25 2026
Total runs:
562.8K
Run Growth:
506.2K
Growth Rate:
96.95%
Total runs:
475.2K
Run Growth:
340.6K
Growth Rate:
75.18%
Total runs:
343.1K
Run Growth:
8.1K
Growth Rate:
2.67%
Total runs:
295.1K
Run Growth:
-219.4K
Growth Rate:
-67.02%
Total runs:
116.5K
Run Growth:
110.0K
Growth Rate:
99.15%
Total runs:
104.2K
Run Growth:
78.6K
Growth Rate:
75.40%
Total runs:
100.4K
Run Growth:
58.9K
Growth Rate:
58.70%
Total runs:
94.0K
Run Growth:
-38.8K
Growth Rate:
-41.26%
Total runs:
82.7K
Run Growth:
5.0K
Growth Rate:
6.01%
Total runs:
66.7K
Run Growth:
61.3K
Growth Rate:
99.02%
Total runs:
61.2K
Run Growth:
-10.4K
Growth Rate:
-17.02%
Total runs:
52.8K
Run Growth:
36.3K
Growth Rate:
68.79%
Total runs:
38.4K
Run Growth:
11.4K
Growth Rate:
29.65%
Total runs:
37.4K
Run Growth:
49.3K
Growth Rate:
100.00%
Total runs:
28.5K
Run Growth:
28.4K
Growth Rate:
92.45%
Total runs:
28.0K
Run Growth:
-5.1K
Growth Rate:
-18.24%
Total runs:
16.7K
Run Growth:
-1.1K
Growth Rate:
-6.75%
Total runs:
16.5K
Run Growth:
2.7K
Growth Rate:
16.31%
Total runs:
15.9K
Run Growth:
9.8K
Growth Rate:
61.57%
Total runs:
15.9K
Run Growth:
4.4K
Growth Rate:
27.90%
Total runs:
15.0K
Run Growth:
-24.0K
Growth Rate:
-159.48%
Total runs:
14.7K
Run Growth:
6.0K
Growth Rate:
40.65%
Total runs:
14.5K
Run Growth:
6.3K
Growth Rate:
42.13%
Total runs:
14.2K
Run Growth:
864
Growth Rate:
6.10%
Total runs:
12.1K
Run Growth:
8.4K
Growth Rate:
69.15%
Total runs:
12.1K
Run Growth:
2.0K
Growth Rate:
16.20%
Total runs:
11.4K
Run Growth:
-28.4K
Growth Rate:
-250.18%
Total runs:
10.6K
Run Growth:
-3.4K
Growth Rate:
-32.50%
Total runs:
10.3K
Run Growth:
2.6K
Growth Rate:
25.11%
Total runs:
8.6K
Run Growth:
3.0K
Growth Rate:
34.97%
Total runs:
6.4K
Run Growth:
4.3K
Growth Rate:
67.01%
Total runs:
6.4K
Run Growth:
3.0K
Growth Rate:
48.60%
Total runs:
6.1K
Run Growth:
-580
Growth Rate:
-9.47%
Total runs:
6.1K
Run Growth:
4.9K
Growth Rate:
81.12%
Total runs:
5.0K
Run Growth:
295
Growth Rate:
5.88%
Total runs:
4.2K
Run Growth:
4.0K
Growth Rate:
97.00%
Total runs:
4.1K
Run Growth:
2.7K
Growth Rate:
67.09%
Total runs:
4.1K
Run Growth:
2.3K
Growth Rate:
55.70%
Total runs:
4.0K
Run Growth:
-1.2K
Growth Rate:
-30.60%
Total runs:
4.0K
Run Growth:
-870
Growth Rate:
-22.03%
Total runs:
3.9K
Run Growth:
2.2K
Growth Rate:
56.04%
Total runs:
3.7K
Run Growth:
3.5K
Growth Rate:
94.87%
Total runs:
3.6K
Run Growth:
3.3K
Growth Rate:
89.81%
Total runs:
3.0K
Run Growth:
-879
Growth Rate:
-28.93%
Total runs:
3.0K
Run Growth:
1.1K
Growth Rate:
39.41%
Total runs:
2.9K
Run Growth:
232
Growth Rate:
7.89%
Total runs:
2.6K
Run Growth:
-11.1K
Growth Rate:
-420.88%
Total runs:
2.5K
Run Growth:
422
Growth Rate:
16.58%
Total runs:
2.4K
Run Growth:
1.9K
Growth Rate:
80.03%
Total runs:
2.4K
Run Growth:
-869
Growth Rate:
-33.14%
Total runs:
2.4K
Run Growth:
101
Growth Rate:
4.27%
Total runs:
2.2K
Run Growth:
-360
Growth Rate:
-15.69%
Total runs:
2.1K
Run Growth:
1.1K
Growth Rate:
51.00%
Total runs:
1.9K
Run Growth:
1.5K
Growth Rate:
75.59%
Total runs:
1.9K
Run Growth:
1.2K
Growth Rate:
63.06%
Total runs:
1.9K
Run Growth:
-591
Growth Rate:
-31.66%
Total runs:
1.8K
Run Growth:
96
Growth Rate:
5.30%
Total runs:
1.8K
Run Growth:
171
Growth Rate:
9.46%
Total runs:
1.7K
Run Growth:
-478
Growth Rate:
-28.49%
Total runs:
1.5K
Run Growth:
268
Growth Rate:
17.91%
Total runs:
1.4K
Run Growth:
-5
Growth Rate:
-0.37%
Total runs:
1.1K
Run Growth:
225
Growth Rate:
19.23%
Total runs:
1.0K
Run Growth:
1.0K
Growth Rate:
97.41%
Total runs:
1.0K
Run Growth:
127
Growth Rate:
12.37%
Total runs:
1.0K
Run Growth:
204
Growth Rate:
20.22%
Total runs:
973
Run Growth:
-29
Growth Rate:
-2.98%
Total runs:
917
Run Growth:
641
Growth Rate:
69.90%
Total runs:
904
Run Growth:
434
Growth Rate:
48.01%
Total runs:
761
Run Growth:
644
Growth Rate:
84.63%
Total runs:
723
Run Growth:
-2
Growth Rate:
-0.27%
Total runs:
712
Run Growth:
-88
Growth Rate:
-12.36%
Total runs:
681
Run Growth:
-9
Growth Rate:
-1.32%
Total runs:
678
Run Growth:
-80
Growth Rate:
-11.80%
Total runs:
617
Run Growth:
-811
Growth Rate:
-131.44%
Total runs:
596
Run Growth:
-101
Growth Rate:
-16.86%
Total runs:
518
Run Growth:
514
Growth Rate:
99.23%
Total runs:
518
Run Growth:
-674
Growth Rate:
-130.12%
Total runs:
516
Run Growth:
-17
Growth Rate:
-3.29%
Total runs:
472
Run Growth:
195
Growth Rate:
41.31%
Total runs:
442
Run Growth:
-117
Growth Rate:
-26.47%
Total runs:
400
Run Growth:
-742
Growth Rate:
-185.50%
Total runs:
385
Run Growth:
1
Growth Rate:
0.26%
Total runs:
362
Run Growth:
18
Growth Rate:
4.97%
Total runs:
355
Run Growth:
-1.3K
Growth Rate:
-366.76%
Total runs:
347
Run Growth:
-26
Growth Rate:
-7.49%