AIPython★ 2,713⑂ 340 forksApache-2.0
syv-ai/HyperQwen
HyperQwen: Qwen on Consumer GPUs
The project optimizes running large Qwen models on available GPUs using vLLM patches and requantization. It achieves 127 tokens/s on 24 GB.
// KEY FEATURES
- Qwen3.8-27B on a single 24 GB GPU
- 127 tokens/s (single user), 1035 tokens/s with 64 parallel
- Context support 150–262k tokens
- vLLM patches and requantization pipeline
#consumer-gpu#cuda#inference-optimization#kv-cache#llm-inference#local-llm#quantization#qwen#qwen3#rtx-3090#speculative-decoding#vllm
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram