base_model, tags, license, language, datasets, pipeline_tag

base_model	tags	license	language	datasets	pipeline_tag
ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth	gguf llama.cpp unsloth lfm2 reasoning quantized	apache-2.0	en	ermiaazarkhalili/Claude-Opus-4.7-Reasoning	text-generation

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

GGUF quantizations of ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth, produced via Unsloth + llama.cpp's conversion scripts.

Field	Value
Source checkpoint	ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth
Base model	LiquidAI/LFM2.5-1.2B-Instruct
Dataset	ermiaazarkhalili/Claude-Opus-4.7-Reasoning
Training	N=1 full epoch (N=1 epoch 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-SFT-Claude-Opus-Reasoning-Unsloth.Q2_K.gguf	smallest	2-bit; extreme compression, quality loss
LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q3_K_M.gguf	small	3-bit; modest quality trade-off
LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q4_K_M.gguf	recommended	4-bit; best size/quality balance
LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q5_K_M.gguf	balanced	5-bit; near-full quality
LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q6_K.gguf	high quality	6-bit; minimal degradation
LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-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

# Text-only
llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF --jinja -p "Explain step-by-step: if a train travels 60 mph for 2.5 hours, how far does it go?" -n 256

# Interactive chat
llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF --jinja -cnv

Ollama

ollama run hf.co/ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF:Q4_K_M

llama-cpp-python

from llama_cpp import Llama
llm = Llama.from_pretrained(
    repo_id="ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF",
    filename="*Q4_K_M.gguf",
    n_ctx=2048,
)
out = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Explain step-by-step: if a train travels 60 mph for 2.5 hours, how far does it go?"}],
    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-SFT-Claude-Opus-Reasoning-Unsloth).
• Distilled reasoning traces reflect patterns from Claude Opus 4.7 and may not generalize to domains outside the distillation corpus.

Citation

@misc{ lfm25_12b_sft_claude_opus_2026_gguf ,
  author = {Ermia Azarkhalili},
  title = { LFM2.5-1.2B-SFT-Unsloth — GGUF quantized },
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF}}
}

---

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