Model Intelligence Sheet
latentdivergence/overlevel-gemma-2-2b-it-Q4_K_M-GGUF overview
license: gemma tags: gguf, gemma2, llama.cpp, on device overlevel gemma 2 2b it Q4 K M GGUF Gemma 2 2B Instruct, quantised to Q4 K M, used on device by the Ove…
Runs locally from ~1.59 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 |
|---|---|---|---|---|
| gemma-2-2b-it-Q4_K_M.gguf | GGUF | Q4_K_M | 1.59 GB | Download |
Model Details
| Model ID | latentdivergence/overlevel-gemma-2-2b-it-Q4_K_M-GGUF |
|---|---|
| Author | latentdivergence |
| Pipeline | — |
| License | gemma |
| Base model | — |
| Last modified | 2026-07-29T17:58:42.000Z |
Model README
---
license: gemma
tags: [gguf, gemma2, llama.cpp, on-device]
---
overlevel-gemma-2-2b-it Q4_K_M GGUF
Gemma 2 2B Instruct, quantised to Q4_K_M, used on-device by the Overlevel Me
Android app via llama.cpp.
- Architecture:
gemma2(Gemma 2 2B Instruct) - Quantisation: Q4_K_M (
general.file_type = 15) - Size: 1,708,582,496 bytes
- SHA-256:
821ed5a8f3e32ce9003957d84a46958533c8de42c5356cb70d81c4dfd2f10961
Named explicitly to avoid confusion with Gemma 4 E2B builds; this is Gemma 2.
Subject to the Gemma Terms of Use.
Run latentdivergence/overlevel-gemma-2-2b-it-Q4_K_M-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models