Model Intelligence Sheet
izyya/Typhoon-Gemma3-Izy-Translate-EN-TH-4B-GGUF overview
tags: gguf llama.cpp unsloth Typhoon Gemma3 Izy Translate EN TH 4B GGUF : GGUF This model was finetuned and converted to GGUF format using Unsloth https://gith…
Runs locally from ~2.32 GB 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 |
|---|---|---|---|---|
| typhoon2.1-gemma3-4b.Q4_K_M.gguf | GGUF | GGUF | 2.32 GB | Download |
Model Details
Model README
---
tags:
- gguf
- llama.cpp
- unsloth
---
Typhoon-Gemma3-Izy-Translate-EN-TH-4B-GGUF : GGUF
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs:
llama-cli -hf izyya/Typhoon-Gemma3-Izy-Translate-EN-TH-4B-GGUF --jinja - For multimodal models:
llama-mtmd-cli -hf izyya/Typhoon-Gemma3-Izy-Translate-EN-TH-4B-GGUF --jinja
Available Model files:
typhoon2.1-gemma3-4b.Q4_K_M.gguf
Note
The model's BOS token behavior was adjusted for GGUF compatibility.
This was trained 2x faster with Unsloth
Run izyya/Typhoon-Gemma3-Izy-Translate-EN-TH-4B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models