unsloth/mistral-7b-instruct-v0.3-bnb-4bit
Quantization vs mistralai/Mistral-7B-Instruct-v0.3. unsloth/mistral-7b-instruct-v0.3-bnb-4bit is a quantized version of the other (U8/BF16).
16 derivatives checked
- Deeokay/mistral-7b-v0.3-llama_tokens-GGUF: Quantization
- ShadowThePessimistic/FANTOME2.0: Quantization
- theprint/CleverBoi-Mistral-0.3-7B: Quantization
- Flexan/FoxyzGPT-1.1-7B-GGUF: Quantization
- theprint/ReWiz-7B: Quantization
- sematemur/openai_gsm8k_finetune_mistral7b_: Quantization
- harshradius/mistal_7b_ft: Quantization
- fardinhossaintherap/mistral_7b_trained_with_augmentoolkit: Quantization
- mondk/Safetensors.claude-sonnet-mistral-7b-it-v0.3: Quantization
- N-Bot-Int/MistThena7B: Quantization
- neph1/bellman-mistral-7b-instruct-v0.3: Quantization
- ayan4m1/Chise-7B: Quantization
- ayan4m1/Claudette-7B: Quantization
- munish0838/Mistral-v0.3-Instruct-Matter-Slim-A: Quantization
- millat/StudyAbroadGPT-7B: Adapter
- ArsParadox/Viel-Mistral-v3: Adapter
10 other repos hold byte-for-byte identical weight files.