Contributors › jvr0x's local-LLM benchmark configs

jvr0x's local-LLM benchmark configs

Every tracked benchmark config measured by jvr0x: model, quant, backend, tokens per second, source-linked and trust-tiered.

Snapshot 2026-09-10 · 148 configs · 69 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

20 configs · 16 models · 4 stars · 92.6 tok/s best single-stream · jvr0x on github.

Configs measured by jvr0x

Model	Quant	Backend	Decode	Trust	Source
Qwen3.6-35B-A3B-NVFP4-Fast (Unsloth)	NVFP4	vllm	92.6 tok/s	Structured table	source
Qwen3.6-35B-A3B-NVFP4-Fast (Unsloth)	NVFP4	vllm	92.6 tok/s	Structured table	source
GPT-OSS-20B	Q4_K_XL	llama.cpp	90.5 tok/s	Structured table	source
Qwen3.6-35B-A3B	Q4_K_XL	llama.cpp	62.7 tok/s	Structured table	source
Ornith-1.0-35B	Q8_0	llama.cpp	56.1 tok/s	Structured table	source
Qwen3-Coder-Next-80B-A3B	Q4_K_XL	llama.cpp	50.1 tok/s	Structured table	source
Qwen3.6-35B-A3B		llama.cpp	48.2 tok/s	Structured table	source
Nemotron-3-Nano-30B-A3B		llama.cpp	47.9 tok/s	Structured table	source
Kimi-Linear-48B-A3B	Q8_0	llama.cpp	47.2 tok/s	Structured table	source
Nemotron-3-Nano-30B-A3B	FP8	vllm	40.7 tok/s	Structured table	source
Gemma-4-12B-IT	Q4_K_M	llama.cpp	28.4 tok/s	Structured table	source
Qwen-AgentWorld-35B-A3B	BF16	vllm	26.9 tok/s	Structured table	source
Qwen3.6-27B-NVFP4 (Unsloth)	NVFP4	vllm	23.3 tok/s	Structured table	source
Qwen3.6-27B-NVFP4 (Unsloth)	NVFP4	vllm	23.3 tok/s	Structured table	source
Gemma-4-26B-A4B-IT	BF16	vllm	22.3 tok/s	Structured table	source
Step-3.7-Flash	IQ4_XS	llama.cpp	19.9 tok/s	Structured table	source
Nex-N2-Pro-397B-A17B		llama.cpp	18.9 tok/s	Structured table	source
Qwopus3.6-27B-Coder	Q8_0	llama.cpp	7.6 tok/s	Structured table	source

More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.