Modelpublic

ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes137downloads

Model Card

LFM2.5-1.2B-xLAM-Unsloth — GGUF quantized

GGUF quantizations of `ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth`, produced via Unsloth + llama.cpp's conversion scripts.

Field	Value
Source checkpoint	`ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth`
Base model	`LiquidAI/LFM2.5-1.2B-Instruct`
Dataset	`Salesforce/xlam-function-calling-60k`
Training	N=1 full epoch (7,500 steps, effective batch=8)
Conversion	Unsloth `save_pretrained_gguf` → llama.cpp GGUF
Quantization tool	llama.cpp `llama-quantize`

Available quantizations

File	Size	Notes
`LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q2_K.gguf`	smallest	2-bit; extreme compression, quality loss
`LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q3_K_M.gguf`	small	3-bit; modest quality trade-off
`LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q4_K_M.gguf`	recommended	4-bit; best size/quality balance
`LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q5_K_M.gguf`	balanced	5-bit; near-full quality
`LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q6_K.gguf`	high quality	6-bit; minimal degradation
`LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q8_0.gguf`	largest	8-bit; closest to bf16 source

Recommended default: Q4_K_M (4-bit, K-quant medium). For memory-constrained deployment, try Q2_K or Q3_K_M. For maximum fidelity, use Q8_0.

Usage

llama.cpp

bash

# Text-only
llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF --jinja -p "Find flights from SFO to NYC on December 25th" -n 256

# Interactive chat
llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF --jinja -cnv

Ollama

bash

ollama run hf.co/ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M

llama-cpp-python

python

from llama_cpp import Llama
llm = Llama.from_pretrained(
    repo_id="ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF",
    filename="*Q4_K_M.gguf",
    n_ctx=2048,
)
out = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Find flights from SFO to NYC on December 25th"}],
    max_tokens=256,
)
print(out["choices"][0]["message"]["content"])

Intended use

For research and non-commercial experimentation only. Outputs should be independently verified before any downstream use.

Limitations

—GGUF quantizations have unavoidable quality loss relative to the source bfloat16 checkpoint. Use Q5_K_M or Q8_0 for best fidelity.
—Inherits all limitations of the source merged checkpoint (`ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth`).
—Limited to the 60 function schemas covered in the training dataset; performance on novel APIs may degrade.

Citation

bibtex

@misc{ lfm25_12b_xlam_unsloth_2026_gguf ,
  author = {Ermia Azarkhalili},
  title = { LFM2.5-1.2B-xLAM-Unsloth — GGUF quantized },
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF}}
}

This lfm2 model was trained 2× faster with Unsloth and Hugging Face's TRL library.