Registry

Browse community-verified serving configurations.

Model	GPU	Framework	Quantization	Throughput	Latency
Qwen3-coder	RTX 4090	vLLM	fp16	3.8k tok/s	12ms	GitHub
Qwen3-coder	A100	vLLM	fp8	6.2k tok/s	8ms	GitHub
Qwen3-coder	H100	TGI	fp8	7.1k tok/s	6ms	GitHub
Qwen3-coder	GB10	vLLM	nvfp4	8.4k tok/s	5ms	GitHub

Qwen3-coder

RTX 4090 · vLLM · fp16

Throughput

3.8k tok/s

Latency

12ms

Qwen3-coder

A100 · vLLM · fp8

Throughput

6.2k tok/s

Latency

8ms

Qwen3-coder

H100 · TGI · fp8

Throughput

7.1k tok/s

Latency

6ms

Qwen3-coder

GB10 · vLLM · nvfp4

Throughput

8.4k tok/s

Latency

5ms