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 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

38 configs · 35 models · 6 stars · 96 tok/s best single-stream · jvr0x on github.

Configs measured by jvr0x

Model	Hardware	Quant	Backend	Decode	Trust	Source
Qwen3.6-35B-heretic	DGX Spark	NVFP4	vllm	96 tok/s	Structured table	source
Qwen3.6-35B-A3B-NVFP4-Fast (Unsloth)	DGX Spark	NVFP4	vllm	92.6 tok/s	Structured table	source
GPT-OSS-20B	DGX Spark	Q4_K_XL	llama.cpp	90.5 tok/s	Structured table	source
Ornith-1.0-35B-AEON	DGX Spark	NVFP4	vllm	84.8 tok/s	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	NVFP4	vllm	77.4 tok/s	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	Q4_K_XL	llama.cpp	62.7 tok/s	Structured table	source
Ornith-1.0-35B	DGX Spark	Q8_0	llama.cpp	56.1 tok/s	Structured table	source
Qwen3-Coder-Next-80B-A3B	DGX Spark	Q4_K_XL	llama.cpp	50.1 tok/s	Structured table	source
Qwen3.6-35B-A3B	DGX Spark		llama.cpp	48.2 tok/s	Structured table	source
Nemotron-3-Nano-30B-A3B	DGX Spark		llama.cpp	47.9 tok/s	Structured table	source
Kimi-Linear-48B-A3B	DGX Spark	Q8_0	llama.cpp	47.2 tok/s	Structured table	source
Nemotron-3-Nano-Omni-30B-A3B	DGX Spark	NVFP4	vllm	41.7 tok/s	Structured table	source
Nemotron-3-Nano-30B-A3B	DGX Spark	FP8	vllm	40.7 tok/s	Structured table	source
Qwen3.6-27B	DGX Spark	NVFP4	vllm (speculative decode, mtp-3)	37.3 tok/s	Structured table	source
Qwen3.8-Flash-Next	DGX Spark	NVFP4	vllm	35.1 tok/s	Structured table	source
Nemotron-Labs-3-Puzzle-75B-A9B	DGX Spark	NVFP4	vllm	32.8 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	DGX Spark		vllm	32.8 tok/s	Structured table	source
Kolibri-1	DGX Spark	FP8	vllm	32 tok/s	Structured table	source
Gemma-4-12B-IT	DGX Spark	Q4_K_M	llama.cpp	28.4 tok/s	Structured table	source
Qwen3.6-27B-AEON	DGX Spark	NVFP4	vllm (speculative decode, dflash-10)	27.9 tok/s	Structured table	source
Laguna-S-2.1	DGX Spark	NVFP4	vllm	27.3 tok/s	Structured table	source
Qwen-AgentWorld-35B-A3B	DGX Spark	BF16	vllm	26.9 tok/s	Structured table	source
Laguna-S-2.1 [nspec=15]	DGX Spark	NVFP4	vllm	25.9 tok/s	Structured table	source
GLM-5.3-Flash	DGX Spark		vllm	25.1 tok/s	Structured table	source
Nemotron-3-Super-120B-A12B	DGX Spark	NVFP4	vllm	24.5 tok/s	Structured table	source

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