unsloth/mistral-7b-v0.3-bnb-4bit

Quantization vs mistralai/Mistral-7B-v0.3. unsloth/mistral-7b-v0.3-bnb-4bit is a quantized version of the other (U8/BF16).

18 derivatives checked

• ebowwa/cognitive-hacker-gguf-0.2: Quantization
• ebowwa/cognitive-hacker-gguf: Quantization
• theprint/CleverBoi-7B-v2: Adapter
• theprint/CleverBoi-7B-v3: Adapter
• theprint/Hemispheres-7B-Right: Quantization
• theprint/Conversely-Mistral-7B: Adapter
• theprint/WorldBuilder-7B-GGUF: Quantization
• theprint/Hemispheres-7B-Combiner: Quantization
• theprint/Hemispheres-7B-Final: Quantization
• theprint/Hemispheres-7B-Left: Quantization
• Johnnylai92/dgtkqabot-mistral-7b-v3: Quantization
• ebowwa/human-biases-io-0.4-gguf: Quantization
• Bharat05092003/llm_ai_v6: Quantization
• llmat/Mistral-v0.3-7B-ORPO: Quantization
• theprint/WorldBuilder-7B: Quantization
• Ramikan-BR/Mis3-7b-v1: Quantization
• DanHauri/mistral7b-malay-tuned: Quantization
• tjohn327/scion_mistral_7b: Quantization

3 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse