---
title: LFM2.5-350M-GGUF
canonical_url: "https://www.modelscope.cn/models/LiquidAI/LFM2.5-350M-GGUF"
md_url: "https://www.modelscope.cn/models/LiquidAI/LFM2.5-350M-GGUF.md"
repository: LiquidAI/LFM2.5-350M-GGUF
last_updated: 2026-09-23
license: other
pipeline_tag: text-generation
tasks:
- text-generation
base_model:
- LiquidAI/LFM2.5-350M
base_model_relation: quantized
library_name:
- transformer
- gguf
- safetensors
- pytorch
frameworks:
- pytorch
language:
- en
- ar
- zh
- fr
- de
- ja
- ko
- es
downloads: 403
stars: 2
tags:
- liquid
- lfm2
- edge
- llama.cpp
- gguf
---
# LFM2.5-350M-GGUF
> LFM2.5-350M-GGUF - LiquidAI 在 ModelScope 开源的模型。Try LFM • Docs • LEAP • Discord
LiquidAI/LFM2.5-350M-GGUF 是 ModelScope 魔搭社区上的text-generation模型，采用 other 许可，基于 LiquidAI/LFM2.5-350M 构建。
- **Repository**: LiquidAI/LFM2.5-350M-GGUF
- **License**: other
- **Tasks**: text-generation
- **Base model**: LiquidAI/LFM2.5-350M
- **Tags**: liquid, lfm2, edge, llama.cpp, gguf
- **Downloads**: 403
- **Stars**: 2
- **Last updated**: 2026-09-23
Source: https://www.modelscope.cn/models/LiquidAI/LFM2.5-350M-GGUF
---
# LFM2.5-350M-GGUF
LFM2 is a new generation of hybrid models developed by [Liquid AI](https://www.liquid.ai/), specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.
Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-350M
## 🏃 How to run LFM2.5
Example usage with [llama.cpp](https://github.com/ggml-org/llama.cpp):
```
llama-cli -hf LiquidAI/LFM2.5-350M-GGUF --conversation \
--temp 0.1 --top-k 50 --repeat-penalty 1.05
```
## QAD Q4_0 GGUF
The Quantization-Aware Distillation (QAD) checkpoint is available as
[`LFM2.5-350M-QAD-Q4_0.gguf`](https://huggingface.co/LiquidAI/LFM2.5-350M-GGUF/blob/main/LFM2.5-350M-QAD-Q4_0.gguf).
This is distinct from the post-training-quantized `LFM2.5-350M-Q4_0.gguf`;
both use the GGUF Q4_0 format.
Example usage with [llama.cpp](https://github.com/ggml-org/llama.cpp):
```
llama-cli -hf LiquidAI/LFM2.5-350M-GGUF \
--hf-file LFM2.5-350M-QAD-Q4_0.gguf \
-p "What is C. elegans?"
```
## QAD source weights (safetensors)
The original FP32 QAD source checkpoint is available in
[`qad/`](https://huggingface.co/LiquidAI/LFM2.5-350M-GGUF/tree/main/qad), with its model config,
tokenizer, generation defaults, and the same chat template as the released QAD GGUF.
It can be loaded in Transformers by passing `subfolder="qad"`:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "LiquidAI/LFM2.5-350M-GGUF"
tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder="qad")
model = AutoModelForCausalLM.from_pretrained(
repo_id, subfolder="qad", dtype="auto", device_map="auto"
)
inputs = tokenizer.apply_chat_template(
[{"role": "user", "content": "What is 2 + 2?"}],
tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
```
These weights are intended for fine-tuning and experimentation. Published QAD
results apply to the Q4_0 GGUF; direct FP32/BF16 inference and other quantization
formats may behave differently. See the [source checkpoint documentation](qad/README.md)
for validation details and the license.
