qwen3-next

Here are 5 public repositories matching this topic...

youssofal / MTPLX

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

Updated Oct 10, 2026
Python

NVIDIA-NeMo / Automodel

Star

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

agent openai llama glm mistral vlm finetuning llm llama3 gemma3 qwen3 gpt-oss qwen3-next minimax-m2 deepseek-v4 gemma4 deepseek-v4-flash kimi-k3 qwen-38-27b

Updated Oct 11, 2026
Python

zipenghao / strata-v100-sm70

Star

Unofficial third-party patches: run Strata (Qwen3.8-Flash-Next) on 2x Tesla V100 sm_70 - platform patches, a PLE correctness fix that garbles output if unpatched, dual-GPU tuning to 43 tok/s @128k

linux cuda patches moe v100 llm-inference gguf speculative-decoding tesla-v100 qwen3-next sm-70

Updated Oct 10, 2026
Shell

alfofire2 / dwarfstar-red-lite

Star

Run Qwen3-Next 80B and Qwen3-Coder on a 24 GB Mac: a DwarfStar-inspired local LLM runtime in native Metal, with expert streaming from the SSD and an OpenAI-compatible server for coding agents.

Updated Oct 10, 2026
C

aws-samples / sample-qwen3-next-on-amazon-bedrock

Star

This repository contains comprehensive sample code demonstrating the unique capabilities of Qwen3-Next models on Amazon Bedrock.

aws bedrock boto3 mixture-of-experts genai amazon-bedrock agentic-workflow qwen3-next qwen3-next-80b-a3b

Updated Jan 29, 2026
Python

Add this topic to your repo

To associate your repository with the qwen3-next topic, visit your repo's landing page and select "manage topics."

Learn more