mistralai/Mistral-Small-3.2-24B-Instruct-2506
Full fine-tune vs mistralai/Mistral-Small-3.1-24B-Base-2503. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 40/131, MLP 192/192, Attention 256/256, other 4/4, lm_head 1/1
68 derivatives checked
- TheDrummer/Cydonia-24B-v4.3-GGUF: Full fine-tune (fewer layers)
- unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF: Same weights, converted (fewer layers)
- Vikhrmodels/Vistral-24B-Instruct: LoRA-style (fewer layers)
- bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF: Same weights, converted (fewer layers)
- lmstudio-community/Mistral-Small-3.2-24B-Instruct-2506-GGUF: Same weights, converted (fewer layers)
- unsloth/Mistral-Small-3.2-24B-Instruct-2506: Identical copy
- mistralai/Magistral-Small-2509: Full fine-tune
- stelterlab/Mistral-Small-3.2-24B-Instruct-2506-FP8: LoRA-style
- huihui-ai/Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated: Abliterated
- jeffcookio/Mistral-Small-3.2-24B-Instruct-2506-awq-sym: Quantization
- Intel/Mistral-Small-3.2-24B-Instruct-2506-int4-AutoRound: Quantization
- TheDrummer/Cydonia-24B-v4.3: Full fine-tune (fewer layers)
- gratex/Mistral-Small-3.2-24B-Instruct-2506-W4A16-AutoRound: Quantization
- Sci-fi-vy/Mistral-Small-3.2-24B-Instruct-2506-GGUF: Same weights, converted (fewer layers)
- Mungert/Magistral-Small-2509-GGUF: Full fine-tune (fewer layers)
- gabriellarson/Mistral-Small-3.2-24B-Instruct-2506-GGUF: Same weights, converted (fewer layers)
- unsloth/Mistral-Small-3.2-24B-Instruct-2506-unsloth-bnb-4bit: Quantization
- eaddario/Mistral-Small-3.2-24B-Instruct-2506-pruned-GGUF: Same weights, converted (fewer layers)
- unsloth/Mistral-Small-3.2-24B-Instruct-2506-bnb-4bit: Quantization
- eaddario/Mistral-Small-3.2-24B-Instruct-2506-GGUF: Same weights, converted (fewer layers)
- jkim96/Mistral-Small-3.2-24B-Instruct-2506-DASHQ-Q2-GGUF: Quantization (fewer layers)
- fabhaus/mistral-small-3.2-24B-Instruct-Abliterated-Q4_K_M: Quantization (fewer layers)
- gratex/mistral-small-3.2-24b-Instruct-GPTQ-W4A16: Quantization
- Qiskit/mistral-small-3.2-24b-qiskit: Full fine-tune
- mlx-community/Mistral-Small-3.2-24B-Instruct-2506-8bit: Quantization
- gratex/mistral-small-3.2-24b-Instruct-2506-NVFP4A16: Quantization
- Deggers/Mistral-Small-3.2-24B-Instruct-2506-mlx-4Bit: Quantization
- nativ-community/Mistral-Small-3.2-24B-Instruct-2506-4bit: Quantization
- anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only: Same weights, repacked (fewer layers)
- ngxson/Home-Cook-Mistral-Small-Omni-24B-2507-GGUF: Full fine-tune (fewer layers)