mistralai/Mistral-Small-24B-Instruct-2501
Full fine-tune vs mistralai/Mistral-Small-24B-Base-2501. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 11/81, MLP 120/120, Attention 160/160, lm_head 1/1
67 derivatives checked
- stelterlab/Mistral-Small-24B-Instruct-2501-AWQ: Quantization
- MaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF: Same weights, converted
- unsloth/Mistral-Small-24B-Instruct-2501: Identical copy
- bartowski/Mistral-Small-24B-Instruct-2501-GGUF: Same weights, converted
- dphn/Dolphin-Mistral-24B-Venice-Edition: Full fine-tune (fewer layers)
- unsloth/Mistral-Small-24B-Instruct-2501-GGUF: Same weights, converted
- RedHatAI/Mistral-Small-24B-Instruct-2501-FP8-dynamic: Quantization
- RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8: Quantization
- Mungert/Dolphin-Mistral-24B-Venice-Edition-GGUF: Full fine-tune
- BasedAGI/Mistral-Small-24B-Instruct-2501-i1-GGUF: Quantization
- unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit: Quantization
- lmstudio-community/Mistral-Small-24B-Instruct-2501-GGUF: Quantization
- mradermacher/Mistral-Small-24B-Instruct-2501-i1-GGUF: Quantization
- dphn/Dolphin-Mistral-24B-Venice-Edition-FP8: Quantization
- ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated: Full fine-tune
- unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit: Quantization
- mlx-community/Mistral-Small-24B-Instruct-2501-4bit: Quantization
- DevQuasar-7/mistralai.Mistral-Small-24B-Instruct-2501-GGUF: Same weights, converted
- professorf/Dolphin-Mistral-24B-Venice-Edition-gguf: Full fine-tune
- mmnga/Mistral-Small-24B-Instruct-2501-gguf: Quantization
- second-state/Mistral-Small-24B-Instruct-2501-GGUF: Same weights, converted
- muranAI/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Full fine-tune
- Shidokaizaki/Dolphin-Mistral-24B-Venice-Edition: Full fine-tune (fewer layers)
- rbinrs/Dolphin-Mistral-24B-Venice-Edition: Full fine-tune (fewer layers)
- EasierAI/Mistral-Small-3-24B: Quantization
- RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w4a16: Quantization
- askalgore/Dolphin-Mistral-24B-Venice-Edition-heretic-2: Full fine-tune
- lemonilia/Mistral-Small-3-Reasoner-s1: LoRA-style
- mradermacher/Mistral-Small-24B-Instruct-2501-GGUF: Quantization
- Mawdistical/Mawdistic-NightLife-24b-GGUF: Full fine-tune