Magistral is a small, efficient reasoning model with 24B parameters.
1.5M Pulls 5 Tags Updated 1 year ago
360 Pulls 3 Tags Updated 2 months ago
36 Pulls 1 Tag Updated 1 year ago
12 Pulls 1 Tag Updated 1 year ago
Suite of weighted quantizations for Magnum V4 models. Available in 9b, 12b, 22b, and 27b. Made by Anthracite-org (Huggingface).
1,797 Pulls 26 Tags Updated 8 months ago
Large dataset roleplaying model finetuned for natural response. Made by ReadyArt (Huggingface).
1,256 Pulls 9 Tags Updated 9 months ago
Leaderboard-topping storytelling model. Made by FlareRebellion (Huggingface).
732 Pulls 11 Tags Updated 9 months ago
Generic all purpose model.
239 Pulls 1 Tag Updated 9 months ago
Mistral Small 3.1
17.9K Pulls 7 Tags Updated 1 year ago
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.
1,756 Pulls 5 Tags Updated 1 year ago
Mistral Small 3.1 24B quantization from bartowski Q6_K with tool support
1,095 Pulls 1 Tag Updated 1 year ago
Q6_K / Q5_K_M / Q4_K_S | mistral-small3.1:24b-instruct-2503
658 Pulls 3 Tags Updated 1 year ago
fine-tuned version of mistralai/Mistral-Small-24B-Instruct-2501, optimized specifically for creative writing tasks. by **lars1234**
509 Pulls 7 Tags Updated 1 year ago
Abliterated version of mistralai/Mistral-Small-Instruct-2409
384 Pulls 1 Tag Updated 1 year ago
Mistral-Small-3.1-24B-Instruct-2503-Q4_K_M
339 Pulls 1 Tag Updated 1 year ago
168 Pulls 4 Tags Updated 1 year ago
34 Pulls 1 Tag Updated 1 year ago
30 Pulls 1 Tag Updated 1 year ago
Base model
27 Pulls 3 Tags Updated 1 year ago
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.
11 Pulls 1 Tag Updated 6 months ago