Rising · Taking off

project-maya

mw00

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

★ 2.1k↑ +4.9%⑂ 272
Rank
#25
On board
—
Move
Steady
Open link ↗
On boardCuda · MIT
stars
2.1k
commits / 13w
616
Contributors
9
Star growth · 1d+100
  • fork 272
  • open issues 53
  • releases 8
hubtrend.app/i/github/mw00/project-mayapushed 8h ago · fetched 1h ago

Repository panorama

from public APIs, independent of our rankings

Health

activity, response time, maintainers
Last push
8h ago
Issue response
24h

median over 100 closed

Open issues
53
Release cadence
v1.0.7

median 0d apart

MITCudacudaglmglm-5llmllm-inferencelocal-llmmixture-of-expertsmoe
mw00/project-maya · 2.1k stars · HubTrend