syv-ai/HyperQwen

HyperQwen

✅ Recently maintained

vLLM patches and requant pipeline run 27B Qwen on one 24GB GPU at 127 tok/s with 150k+ context.

2,492Stars
318Forks
+2267-day stars

Python · Apache-2.0 · Last push 2026-10-30

Official repository & installation ↗
kv-cachellm-inferencelocal-llmquantizationqwenqwen3rtx-3090speculative-decodingvllmconsumer-gpu

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-08-102026-11-03
View historical data
DateStars
2026-10-051,860
2026-10-061,874
2026-10-071,887
2026-10-081,903
2026-10-091,919
2026-10-101,932
2026-10-111,951
2026-10-121,965
2026-10-131,985
2026-10-141,999
2026-10-152,015
2026-10-162,027
2026-10-172,033
2026-10-182,074
2026-10-192,112
2026-10-202,134
2026-10-212,153
2026-10-222,182
2026-10-232,192
2026-10-242,209
2026-10-252,227
2026-10-262,252
2026-10-272,289
2026-10-282,391
2026-10-292,418
2026-10-302,447
2026-10-312,460
2026-11-012,473
2026-11-022,487
2026-11-032,492

Get the project

git clone https://github.com/syv-ai/HyperQwen.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

nanobot

Lightweight swarm intelligence experimental platform for micro-agents.

★ 49,776vllm

High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.

★ 96,180litellm

Call 100+ LLM APIs using the OpenAI input/output format.

★ 62,604