Language Models
RWKV/rwkv.cpp
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
C++MITupdated Mar 23, 2025
🏆 #555 overall#170 of 601 in Language Models
dvmazur /mixtral-offloading
Run Mixtral-8x7B models in Colab or consumer desktops
$ git clone https://github.com/dvmazur/mixtral-offloading.gitStars
2.3K
2,335
Forks
225
225
Language
Python
License
MIT
Created
Dec 15, 2023
2.8 years old
Last push
Apr 8, 2024
Categories
More in Language Models
Language Models
RahulSChand/gpu_poor
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
JavaScriptno licenseupdated Dec 3, 2024
Language Models
AviSoori1x/makeMoE
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
Jupyter NotebookMITupdated Oct 30, 2024
Language Models
mlc-ai/web-llm
High-performance In-browser LLM Inference Engine
TypeScriptApache-2.0updated Sep 15, 2026
Language Models
BlinkDL/RWKV-LM🔥 active
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
PythonApache-2.0updated Sep 21, 2026
Language Models
Data from GitHub · snapshot Sep 24, 2026