🏆 #777 overall#182 of 1,378 in Language Models

dvmazur /mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

$ git clone https://github.com/dvmazur/mixtral-offloading.git
GitHub social preview for dvmazur/mixtral-offloading
Stars
2.3K
2,334
This week
0 ★
-2 this month
Forks
224
224
Language
Python
License
MIT
Created
Dec 15, 2023
2.9 years old
Last push
Apr 8, 2024

Stars, last 30 days

Oct 15, 2026 → Nov 16, 2026
★ 2.3K▼ 1★ 2.3K

Categories

GitHub topics

More in Language Models

Language Models

RWKV/rwkv.cpp

▲ +1 ★ this week

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

C++MITupdated Mar 23, 2025
GitHub ↗★ 1.6K⑂ 130
Language Models

RahulSChand/gpu_poor

▲ +3 ★ this week

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

JavaScriptno licenseupdated Dec 3, 2024
GitHub ↗★ 1.4K⑂ 88
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
GitHub ↗★ 821⑂ 96
Language Models

mlc-ai/web-llm🔥 active

▲ +18 ★ this week

High-performance In-browser LLM Inference Engine

TypeScriptApache-2.0updated Nov 15, 2026
GitHub ↗★ 19.4K⑂ 1.4K
Language Models

BlinkDL/RWKV-LM

▲ +5 ★ this week

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 Nov 4, 2026
GitHub ↗★ 14.8K⑂ 1K
Language Models

mlfoundations/open_clip🔥 active

▲ +22 ★ this week

An open source implementation of CLIP.

PythonOtherupdated Nov 10, 2026
GitHub ↗★ 14.3K⑂ 1.3K

Data from GitHub · snapshot Nov 16, 2026