Model Intelligence Sheet
nphearum/Opus4.8-tuned-super-fast-GGUF overview
Opus4.8 tuned super fast GGUF : GGUF This model was finetuned and converted to GGUF format Example usage : For text only LLMs: llama cli hf nphearum/Opus4.8 tu…
Runs locally from ~492.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
8 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LFM2.5-1.2B-Instruct.BF16.gguf | GGUF | GGUF | 2.18 GB | Download |
| LFM2.5-1.2B-Instruct.F16.gguf | GGUF | GGUF | 2.18 GB | Download |
| LFM2.5-1.2B-Instruct.Q2_K_L.gguf | GGUF | GGUF | 492.0 MB | Download |
| LFM2.5-1.2B-Instruct.Q3_K_M.gguf | GGUF | GGUF | 572.5 MB | Download |
| LFM2.5-1.2B-Instruct.Q4_K_M.gguf | GGUF | GGUF | 697.0 MB | Download |
| LFM2.5-1.2B-Instruct.Q5_K_M.gguf | GGUF | GGUF | 804.3 MB | Download |
| LFM2.5-1.2B-Instruct.Q6_K.gguf | GGUF | GGUF | 918.2 MB | Download |
| LFM2.5-1.2B-Instruct.Q8_0.gguf | GGUF | GGUF | 1.16 GB | Download |
Model Details
Model README
---
tags:
- gguf
- llama.cpp
- unsloth
---
Opus4.8-tuned-super-fast-GGUF : GGUF
This model was finetuned and converted to GGUF format
Example usage:
- For text only LLMs:
llama-cli -hf nphearum/Opus4.8-tuned-super-fast-GGUF --jinja - For multimodal models:
llama-mtmd-cli -hf nphearum/Opus4.8-tuned-super-fast-GGUF --jinja
Run nphearum/Opus4.8-tuned-super-fast-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models