GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

Ma7ee7/Qwen3.8_1.2B_LFM_Distillation_GGUF overview

Qwen3.8 1.2B LFM Distillation GGUF : GGUF This model was finetuned and converted to GGUF format using Unsloth https://github.com/unslothai/unsloth . Example us…

gguflfm2llama.cppunslothendpoints_compatibleregion:usconversational

Runs locally from ~697.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
LFM2.5-1.2B-Thinking.Q4_K_M.ggufGGUFGGUF697.0 MBDownload
LFM2.5-1.2B-Thinking.Q5_K_M.ggufGGUFGGUF804.3 MBDownload
LFM2.5-1.2B-Thinking.Q8_0.ggufGGUFGGUF1.16 GBDownload

Model Details

Model IDMa7ee7/Qwen3.8_1.2B_LFM_Distillation_GGUF
AuthorMa7ee7
Pipeline
License
Base model
Last modified2026-08-05T23:05:47.000Z

Model README

---

tags:

  • gguf
  • llama.cpp
  • unsloth

---

Qwen3.8_1.2B_LFM_Distillation_GGUF : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf Ma7ee7/Qwen3.8_1.2B_LFM_Distillation_GGUF --jinja
  • For multimodal models: llama-mtmd-cli -hf Ma7ee7/Qwen3.8_1.2B_LFM_Distillation_GGUF --jinja

Available Model files:

  • LFM2.5-1.2B-Thinking.Q8_0.gguf
  • LFM2.5-1.2B-Thinking.Q5_K_M.gguf
  • LFM2.5-1.2B-Thinking.Q4_K_M.gguf

This was trained 2x faster with Unsloth

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>

Run Ma7ee7/Qwen3.8_1.2B_LFM_Distillation_GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models