mistralai/Ministral-3-14B-Reasoning-2512
Full fine-tune vs mistralai/Ministral-3-14B-Base-2512. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 123/131, MLP 192/192, Attention 256/256, other 4/4, lm_head 1/1
29 derivatives checked
- MaziyarPanahi/Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- lmstudio-community/Ministral-3-14B-Reasoning-2512-GGUF: Quantization (fewer layers)
- tiny-random/mistral-3: Different architecture
- unsloth/Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- mistralai/Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- bartowski/mistralai_Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- mradermacher/Ministral-3-14B-Reasoning-2512-i1-GGUF: Quantization (fewer layers)
- ccharnkij/Ministral-3-14B-Reasoning-2512-Uncensored-GGUF: LoRA-style (fewer layers)
- ggml-org/Ministral-3-14B-Reasoning-2512-GGUF: Quantization (fewer layers)
- EnlistedGhost/Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- eaddario/Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF: Same weights, converted (fewer layers)
- mradermacher/Ministral-3-14B-Reasoning-2512-GGUF: Quantization (fewer layers)
- cyankiwi/Ministral-3-14B-Reasoning-2512-AWQ-4bit: Quantization
- jkim96/Ministral-3-14B-Reasoning-2512-DASHQ-Q2-GGUF: Quantization (fewer layers)
- DevQuasar/mistralai.Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- unsloth/Ministral-3-14B-Reasoning-2512-bnb-4bit: Quantization
- s3dev-ai/Ministral-3-14B-Reasoning-2512-gguf: Same weights, converted (fewer layers)
- pbhappliedsystems/ministral-3-14b-reasoning-2512-gguf-Q4-K-M: Quantization (fewer layers)
- unsloth/Ministral-3-14B-Reasoning-2512: Identical copy
- unsloth/Ministral-3-14B-Reasoning-2512-unsloth-bnb-4bit: Quantization
- an0nya/Ministral-3-14B-Reasoning-2512-oQ4e: Quantization
- spotapovadm/Ministral-3-14B-Reasoning-2512-GGUF: Same weights, converted (fewer layers)
- ggfox00000/Ministral-3-14B-Reasoning-2512-GGUF: Quantization (fewer layers)
- yujiepan/mistral-3-tiny-random: Different architecture
- MuXodious/Ministral-3-14B-Reasoning-2512-absolute-heresy: Abliterated
- ccharnkij/Ministral-3-14B-Reasoning-2512-Uncensored: LoRA-style
- ValiantLabs/Ministral-3-14B-Reasoning-2512-Esper3.1: LoRA-style
- ValiantLabs/Ministral-3-14B-Reasoning-2512-ShiningValiant3: LoRA-style