48 lines
2.6 KiB
Markdown
48 lines
2.6 KiB
Markdown
---
|
|
tags:
|
|
- gguf
|
|
- llama.cpp
|
|
- quantized
|
|
- text-generation
|
|
license: other
|
|
base_model: TheDrummer/Gemmasutra-Small-4B-v1
|
|
datasets:
|
|
- Gemmasutra-Small-4B-v1
|
|
|
|
---
|
|
|
|
# Gemmasutra-Small-4B-v1 GGUF Quantized Models
|
|
|
|
## Model Information
|
|
- **Base Model:** [TheDrummer/Gemmasutra-Small-4B-v1](https://huggingface.co/TheDrummer/Gemmasutra-Small-4B-v1)
|
|
- **Quantized by:** [matrixportal](https://huggingface.co/matrixportal)
|
|
- **Format:** GGUF (for llama.cpp compatible tools)
|
|
- **Quantized on:** 2025-04-09
|
|
|
|
## Recommended Downloads
|
|
- **Q4_K_M:** [`gemmasutra-small-4b-v1.q4_k_m.gguf`](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q4_k_m.gguf)
|
|
- **Q4_0:** [`gemmasutra-small-4b-v1.q4_0.gguf`](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q4_0.gguf)
|
|
- **Q8_0:** [`gemmasutra-small-4b-v1.q8_0.gguf`](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q8_0.gguf)
|
|
|
|
## All Available Quantizations
|
|
| File | Download |
|
|
|------|----------|
|
|
| `gemmasutra-small-4b-v1.f16.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.f16.gguf) |
|
|
| `gemmasutra-small-4b-v1.q2_k.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q2_k.gguf) |
|
|
| `gemmasutra-small-4b-v1.q3_k_m.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q3_k_m.gguf) |
|
|
| `gemmasutra-small-4b-v1.q4_0.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q4_0.gguf) |
|
|
| `gemmasutra-small-4b-v1.q4_k_m.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q4_k_m.gguf) |
|
|
| `gemmasutra-small-4b-v1.q5_k_m.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q5_k_m.gguf) |
|
|
| `gemmasutra-small-4b-v1.q6_k.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q6_k.gguf) |
|
|
| `gemmasutra-small-4b-v1.q8_0.gguf` | [Download](https://huggingface.co/matrixportal/Gemmasutra-Small-4B-v1-GGUF/resolve/main/gemmasutra-small-4b-v1.q8_0.gguf) |
|
|
|
|
## Usage Instructions
|
|
1. Download desired GGUF file
|
|
2. Use with compatible tools:
|
|
- [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
|
- [Ollama](https://ollama.ai/)
|
|
- [LM Studio](https://lmstudio.ai/)
|
|
- [GPT4All](https://gpt4all.io)
|
|
|
|
💡 **Tip:** Q4_K_M offers the best balance for most use cases.
|