Contributors › kyuz0's local-LLM benchmark configs

kyuz0's local-LLM benchmark configs

Every tracked benchmark config measured by kyuz0: 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.

40 configs · 5 models · 1915 stars · 74.6 tok/s best single-stream · kyuz0 on github.

Configs measured by kyuz0

Model	Quant	Backend	Decode	Trust	Source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/vulkan	74.6 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/vulkan	72.8 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/rocm	68.3 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/rocm	64.5 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/vulkan-radv	62.8 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/vulkan-radv-performance	62.2 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/vulkan	58.7 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/rocm-7.14	53.5 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/rocm-7.14-pr26592	53 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/rocm-7.2.4	51.7 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q8_K_XL	llama.cpp/vulkan-radv	49.2 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q8_K_XL	llama.cpp/vulkan-radv-performance	48.9 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q4_K_XL	llama.cpp/rocm	48.7 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q8_K_XL	llama.cpp/rocm-7.14	48.1 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q8_K_XL	llama.cpp/rocm-7.14-pr26592	47.9 tok/s	Structured table	source
Qwen3.6-35B-A3B	UD-Q8_K_XL	llama.cpp/rocm-7.2.4	46.5 tok/s	Structured table	source
gemma-4-26B-A4B-it	UD-Q8_K_XL	llama.cpp/rocm-7.2.4	41.8 tok/s	Structured table	source
Qwen3.5-122B-A10B	UD-Q4_K_XL	llama.cpp/rocm-7.2.4	21.6 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	UD-IQ3_XXS	llama.cpp/vulkan-radv-performance	19.8 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	UD-IQ2_XXS	llama.cpp/rocm-7.14	16.2 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	UD-IQ2_XXS	llama.cpp/rocm-7.2.4	16.1 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	UD-IQ3_XXS	llama.cpp/rocm-7.14	16 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	UD-IQ3_XXS	llama.cpp/rocm-7.2.4	15.8 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	UD-IQ2_XXS	llama.cpp/rocm-7.14-pr26592	14.8 tok/s	Structured table	source
DeepSeek-V4-Flash-0731	UD-IQ3_XXS	llama.cpp/rocm-7.14-pr26592	14.5 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.