20+ models
Magistral is a small, efficient reasoning model with 24B parameters.
This is the Q4_K converted version of the original Qiskit/mistral-small-3.2-24b-qiskit provided by IBM's Qiskit Huggingface. Please refer to the original mistral-small-3.2-24b-qiskit model card for more details.
FlareRebellion/WeirdCompound-v1.2-24b
anthracite-org/magnum-v4-27b-gguf
Suite of weighted quantizations for Magnum V4 models. Available in 9b, 12b, 22b, and 27b. Made by Anthracite-org (Huggingface).
Large dataset roleplaying model finetuned for natural response. Made by ReadyArt (Huggingface).
Leaderboard-topping storytelling model. Made by FlareRebellion (Huggingface).
Generic all purpose model.
Mistral Small 3.1
Mistral-Small-3.1-24B-Instruct-2503 is a quantized GGUF variant of Mistral-small 3.1 24B Instruct (2503), optimized to run smoothly on GPUs with as low as 16GB VRAM.
This model is Mistral-small-24b-Instruct-2501 fine-tuned on ~13k Climsight data which are pairs of prompts/completions extracted from climsight pipeline. Below are all the technical specs of the fine-tuning process along with the evaluation used.
Mistral Small 3.1 24B quantization from bartowski Q6_K with tool support
Q6_K / Q5_K_M / Q4_K_S | mistral-small3.1:24b-instruct-2503
fine-tuned version of mistralai/Mistral-Small-24B-Instruct-2501, optimized specifically for creative writing tasks. by **lars1234**
128k context; no vision yet; Q8, Q6_K
Abliterated version of mistralai/Mistral-Small-Instruct-2409