mistralai/Mixtral-8x7B-Instruct-v0.1
Full fine-tune vs mistralai/Mixtral-8x7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, MLP 768/768, other 32/32, Norms 65/65, Attention 128/128, lm_head 1/1
37 derivatives checked
- TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF: Not comparable yet
- Lucy-in-the-Sky/Mixtral-8x7B-Instruct-v0.1-Q4_K_M-GGUF: Quantization
- GritLM/GritLM-8x7B: Full fine-tune
- RedHatAI/Mixtral-8x7B-Instruct-v0.1: Identical copy
- MaziyarPanahi/Mixtral-8x7B-Instruct-v0.1-GGUF: Not comparable yet
- second-state/Mixtral-8x7B-Instruct-v0.1-GGUF: Not comparable yet
- TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ: Quantization
- TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ: Quantization
- amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV: Quantization
- mradermacher/Mixtral-8x7B-Instruct-v0.1-GGUF: Quantization
- tensorblock/Mixtral-8x7B-Instruct-v0.1-GGUF: Quantization
- mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF: Quantization
- amd/Mixtral-8x7B-Instruct-v0.1-w8a8-llmcompressor-v0.10.0.2: Quantization
- amd/Mixtral-8x7B-Instruct-v0.1-w4a16-llmcompressor: Quantization
- qwp4w3hyb/Mixtral-8x7B-Instruct-v0.1-iMat-GGUF: Not comparable yet
- ApolloRaines/Mixtral-8x7B-Instruct-v0.1-Parasite: Partial fine-tune
- rizla/rizla-17: Full fine-tune
- bartowski/Cerebrum-1.0-8x7b-GGUF-old: Not comparable yet
- apple/sage-ft-mixtral-8x7b: LoRA-style
- continuum-ai/mixtral-8x7b-instruct-compacted-conservative: LoRA-style
- unsloth/Mixtral-8x7B-Instruct-v0.1-unsloth-bnb-4bit: Quantization
- Chemin-AI/Mixtral-8x7B-Instruct-v0.1-gguf: Quantization
- argilla/notux-8x7b-v1: Full fine-tune
- Aratako/Mixtral-8x7B-Instruct-v0.1-upscaled: Partial fine-tune (fewer layers)
- unsloth/Mixtral-8x7B-Instruct-v0.1: Identical copy
- vicgalle/Merge-Mixtral-Prometheus-8x7B: Full fine-tune
- ykarout/Mixtral-8x7B-DeepSeek-R1-Distill: LoRA-style
- orangetin/OpenHermes-Mixtral-8x7B: Full fine-tune
- Na0s/Mixtral-8x7B-v0.1-instruct-l2-norm-post-Gates-LoRA-SFT-pruned-3-experts: LoRA-style (fewer layers)
- Na0s/Mixtral-8x7B-v0.1-instruct-l2-norm-post-Gates-LoRA-SFT-pruned-1-expert: LoRA-style
37 other repos hold byte-for-byte identical weight files.