Model Intelligence Sheet
qikp/LFM2.5-230M-Thinking-v2-GGUF overview
These are simple quantizations of qikp/LFM2.5 230M Thinking v2 https://huggingface.co/qikp/LFM2.5 230M Thinking v2 using llama.cpp.
Runs locally from ~440.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| BF16.gguf | GGUF | BF16 | 440.5 MB | Download |
Model Details
| Model ID | qikp/LFM2.5-230M-Thinking-v2-GGUF |
|---|---|
| Author | qikp |
| Pipeline | text-generation |
| License | — |
| Base model | qikp/LFM2.5-230M-Thinking-v2 |
| Last modified | 2026-07-30T20:29:57.000Z |
Model README
---
base_model:
- qikp/LFM2.5-230M-Thinking-v2
pipeline_tag: text-generation
quantized_by: qikp
---
These are simple quantizations of qikp/LFM2.5-230M-Thinking-v2 using llama.cpp.
Run qikp/LFM2.5-230M-Thinking-v2-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models