GraySoft
Model Comparison

maziyarpanahi/mixtral-8x22b-v0.1-ggufvsunsloth/deepseek-r1-distill-llama-8b-gguf

Side-by-side comparison of maziyarpanahi/mixtral-8x22b-v0.1-gguf and unsloth/deepseek-r1-distill-llama-8b-gguf: downloads, license, context length, tasks, and benchmarks.

maziyarpanahi/mixtral-8x22b-v0.1-gguf

MaziyarPanahi · text-generation

On April 10th, @MistralAI released a model named "Mixtral 8x22B," an 176B MoE via magnet link (torrent): The GGUF and quantized models here are based on v2ray/Mixtral-8x22B-v0.1 model

unsloth/deepseek-r1-distill-llama-8b-gguf

unsloth · text-generation

We have a free Google Colab notebook for turning Llama 3.1 (8B) into a reasoning model: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb

Side-by-side Specifications

maziyarpanahi/mixtral-8x22b-v0.1-ggufunsloth/deepseek-r1-distill-llama-8b-gguf
AuthorMaziyarPanahiunsloth
Pipeline Tasktext-generationtext-generation
Librarytransformerstransformers
Downloads89,59741,456
Likes75295
LicenseUnknownUnknown
Context Length
Created2024-04-102025-01-20
Last Modified2024-04-152025-05-10
Tags
transformersggufmixtraltext-generationquantized2-bit3-bit4-bit5-bit6-bit
transformersggufllamatext-generationdeepseekunslothllama-3metaenarxiv:2501.12948

View full details: maziyarpanahi/mixtral-8x22b-v0.1-gguf · unsloth/deepseek-r1-distill-llama-8b-gguf