Contributors › paulplee's local-LLM benchmark configs

paulplee's local-LLM benchmark configs

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

Snapshot 2026-10-15 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

68 configs · 5 models · 66.3 tok/s best single-stream · paulplee on huggingface.

Configs measured by paulplee

Model	Hardware	Quant	Backend	Decode	Context	Trust	Source
Qwen3.6-35B-A3B	DGX Spark	UD-IQ3_XXS	llama.cpp/cuda	66.3 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-IQ3_S	llama.cpp/cuda	65.6 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q3_K_XL	llama.cpp/cuda	64.1 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q3_K_M	llama.cpp/cuda	64 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-IQ4_NL	llama.cpp/cuda	63.8 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-IQ4_XS	llama.cpp/cuda	63.3 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-IQ4_NL_XL	llama.cpp/cuda	63.1 tok/s	8192	Structured table	source
gemma-4-26B-A4B-it	DGX Spark	UD-IQ3_XXS	llama.cpp/cuda	62.9 tok/s	8192	Structured table	source
gemma-4-26B-A4B-it	DGX Spark	UD-IQ3_S	llama.cpp/cuda	62.7 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q4_K_S	llama.cpp/cuda	62.1 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	MXFP4	llama.cpp/cuda	61.4 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q4_K_M	llama.cpp/cuda	61 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q3_K_S	llama.cpp/cuda	61 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q4_K_XL	llama.cpp/cuda	59.7 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q5_K_S	llama.cpp/cuda	57.8 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q5_K_M	llama.cpp/cuda	57.5 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q5_K_XL	llama.cpp/cuda	57.2 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q6_K	llama.cpp/cuda	56 tok/s	8192	Structured table	source
gemma-4-26B-A4B-it	DGX Spark	UD-IQ4_XS	llama.cpp/cuda	55.8 tok/s	8192	Structured table	source
gemma-4-26B-A4B-it	DGX Spark	UD-IQ4_NL	llama.cpp/cuda	55.5 tok/s	8192	Structured table	source
gemma-4-26B-A4B-it	DGX Spark	MXFP4	llama.cpp/cuda	54.9 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	UD-Q6_K_XL	llama.cpp/cuda	51.1 tok/s	8192	Structured table	source
Qwen3.6-35B-A3B	DGX Spark	Q8_0	llama.cpp/cuda	50.2 tok/s	8192	Structured table	source
Qwen3.5-9B	DGX Spark	UD-IQ3_XXS	llama.cpp/cuda	49.2 tok/s	8192	Structured table	source
gemma-4-26B-A4B-it	DGX Spark	Q8_0	llama.cpp/cuda	47.5 tok/s	8192	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.