MaziyarPanahi / gemma-2 family / text-generation
gemma-2-2b-it-GGUF
MaziyarPanahi/gemma-2-2b-it-GGUF
Run locally Smallest indexed GGUF / needs Ollama
ollama run hf.co/MaziyarPanahi/gemma-2-2b-it-GGUF/gemma-2-2b-it.IQ1_S.gguf Benchmarks
Where it scores.
General Provisional —
Coding Provisional —
Math Provisional —
Reasoning Provisional —
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| Q4 / smallest | GGUF | 832 MB | — | gemma-2-2b-it.IQ1_S.gguf |
| Q4 | GGUF | 874 MB | — | gemma-2-2b-it.IQ1_M.gguf |
| Q4 | GGUF | 1.0 GB | — | gemma-2-2b-it.IQ2_XS.gguf |
| Q2_K | GGUF | 1.2 GB | — | gemma-2-2b-it.Q2_K.gguf |
| Q4 | GGUF | 1.3 GB | — | gemma-2-2b-it.IQ3_XS.gguf |
| Q3_K_S | GGUF | 1.4 GB | — | gemma-2-2b-it.Q3_K_S.gguf |
| Q3_K_M | GGUF | 1.5 GB | — | gemma-2-2b-it.Q3_K_M.gguf |
| Q3_K_L | GGUF | 1.6 GB | — | gemma-2-2b-it.Q3_K_L.gguf |
| Q4 | GGUF | 1.6 GB | — | gemma-2-2b-it.IQ4_XS.gguf |
| Q4_K_S | GGUF | 1.6 GB | — | gemma-2-2b-it.Q4_K_S.gguf |
| Q4_K_M | GGUF | 1.7 GB | — | gemma-2-2b-it.Q4_K_M.gguf |
| Q5_K_S | GGUF | 1.9 GB | — | gemma-2-2b-it.Q5_K_S.gguf |
| Q5_K_M | GGUF | 1.9 GB | — | gemma-2-2b-it.Q5_K_M.gguf |
| Q6_K | GGUF | 2.2 GB | — | gemma-2-2b-it.Q6_K.gguf |
| Q8_0 | GGUF | 2.8 GB | — | gemma-2-2b-it.Q8_0.gguf |
| Q4 | GGUF | 5.2 GB | — | gemma-2-2b-it.fp16.gguf |
Sizes are file sizes, not peak runtime memory.
From the Hugging Face model card
About this model.
From the Hugging Face model card
About this model.
MaziyarPanahi/gemma-2-2b-it-GGUF
- Model creator: google
- Original model: google/gemma-2-2b-it
Description
MaziyarPanahi/gemma-2-2b-it-GGUF contains GGUF format model files for google/gemma-2-2b-it.
About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
- llama.cpp. The source project for GGUF. Offers a CLI and a server option.
- llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
- LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
- text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
- KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
- GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
- LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
- Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
- candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
- ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
Special thanks
🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.