DevQuasar-6/mistralai.Mistral-Small-3.1-24B-Base-2503-GGUF

Same weights, converted (fewer layers) vs mistralai/Mistral-Small-3.1-24B-Base-2503. DevQuasar-6/mistralai.Mistral-Small-3.1-24B-Base-2503-GGUF matches part of mistralai/Mistral-Small-3.1-24B-Base-2503 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.1-24B-Base-2503 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse