e1n00r/tinyserve
30 tok/s for 20B MoE on 8 GB VRAM. Flat throughput to 32K context. Native MXFP4 + GGUF Q4_K/Q5_K/Q6_K via ggml CUDA kernels — zero dequant. Expert offloading for models that don't fit in GPU memory.
21
Stars
4
Forks
24.2
Radar Score
Stable
Momentum
Scoring Breakdown
Impact12.7
Velocity26.8
Health39.0
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python