--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - mistral - trl base_model: unsloth/mistral-7b-bnb-4bit datasets: - gate369/Alpaca-Star quantized_by: bartowski pipeline_tag: text-generation --- ## Llamacpp Quantizations of Mistral-quiet-star-demo Using llama.cpp release b2536 for quantization. Original model: https://huggingface.co./liminerity/Mistral-quiet-star-demo Download a file (not the whole branch) from below: | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [Mistral-quiet-star-Q8_0.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. | | [Mistral-quiet-star-Q6_K.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-GGUF/blob/main/Mistral-quiet-star-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. | | [Mistral-quiet-star-Q5_K_M.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-GG-demoUF/blob/main/Mistral-quiet-star-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. | | [Mistral-quiet-star-Q5_K_S.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. | | [Mistral-quiet-star-Q5_0.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. | | [Mistral-quiet-star-Q4_K_M.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, uses about 4.83 bits per weight. | | [Mistral-quiet-star-Q4_K_S.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. | | [Mistral-quiet-star-IQ4_NL.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-IQ4_NL.gguf) | IQ4_NL | 4.15GB | Decent quality, similar to Q4_K_S, new method of quanting, | | [Mistral-quiet-star-IQ4_XS.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-IQ4_XS.gguf) | IQ4_XS | 3.94GB | Decent quality, new method with similar performance to Q4. | | [Mistral-quiet-star-Q4_0.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. | | [Mistral-quiet-star-Q3_K_L.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. | | [Mistral-quiet-star-Q3_K_M.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. | | [Mistral-quiet-star-IQ3_M.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-IQ3_M.gguf) | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance. | | [Mistral-quiet-star-IQ3_S.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-IQ3_S.gguf) | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3 quants. | | [Mistral-quiet-star-Q3_K_S.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. | | [Mistral-quiet-star-Q2_K.gguf](https://huggingface.co./bartowski/Mistral-quiet-star-demo-GGUF/blob/main/Mistral-quiet-star-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski