mistralai/Mistral-Small-3.1-24B-Instruct-2503
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
57 derivatives checked
- mistralai/Magistral-Small-2506: Full fine-tune (fewer layers)
- ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g: Quantization
- RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic: Quantization
- unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Same weights, converted (fewer layers)
- mistralai/Devstral-Small-2507: Full fine-tune (fewer layers)
- bartowski/mistralai_Mistral-Small-3.1-24B-Instruct-2503-GGUF: Same weights, converted (fewer layers)
- mistralai/Magistral-Small-2507: Full fine-tune (fewer layers)
- Mungert/Harbinger-24B-GGUF: Full fine-tune (fewer layers)
- lmstudio-community/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Quantization (fewer layers)
- mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF: Quantization (fewer layers)
- mistralai/Devstral-Small-2505: Full fine-tune (fewer layers)
- Mungert/Magistral-Small-2506-GGUF: Full fine-tune (fewer layers)
- RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16: Quantization
- DavidAU/Mistral-Small-3.1-24B-Instruct-2503-MAX-NEO-Imatrix-GGUF: Quantization (fewer layers)
- OPEA/Mistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-awq-sym: Quantization
- RedHatAI/Mistral-Small-3.1-24B-Instruct-2503: Identical copy
- EnlistedGhost/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Same weights, converted (fewer layers)
- second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Same weights, converted (fewer layers)
- RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8: Quantization
- merterbak/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Quantization (fewer layers)
- mradermacher/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Quantization (fewer layers)
- gaianet/Mistral-Small-3.1-24B-Instruct-2503-GGUF: Same weights, converted (fewer layers)
- unsloth/Mistral-Small-3.1-24B-Instruct-2503: Identical copy
- TheDrummer/Cydonia-24B-v3-GGUF: Full fine-tune (fewer layers)
- unsloth/Devstral-Small-2507: Full fine-tune (fewer layers)
- DevQuasar-6/mrfakename.mistral-small-3.1-24b-instruct-2503-hf-GGUF: Same weights, converted (fewer layers)
- OPEA/Mistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-gptq-sym: Quantization
- jkim96/Mistral-Small-3.1-24B-Instruct-2503-DASHQ-Q2-GGUF: Quantization (fewer layers)
- openfree/Mistral-Small-3.1-24B-Instruct-2503-Q4_K_M-GGUF: Quantization (fewer layers)
- DevQuasar-6/mistralai.Mistral-Small-3.1-24B-Instruct-2503-GGUF: Same weights, converted (fewer layers)