Contributors › sypherin's local-LLM benchmark configs
sypherin's local-LLM benchmark configs
Every tracked benchmark config measured by sypherin: 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.
4 configs · 3 models · 73 stars · 66 tok/s best single-stream · sypherin on github.
Configs measured by sypherin
| Model | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|
| Qwen3.6-35B-A3B-MTP | UD-Q4_K_XL | vulkan | 66 tok/s | 262144 | Verified (ran it) | source |
| Qwen3.6-35B-A3B | UD-Q8_K_XL | llama.cpp/vulkan | 41 tok/s | Verified (ran it) | source | |
| Qwen3.6-35B-A3B | UD-Q8_K_XL | llama.cpp/rocm | 39 tok/s | Verified (ran it) | source | |
| Qwen3.8-27B | UD-Q4_K_XL | llama.cpp/vulkan | 24.6 tok/s | 131072 | Verified (ran it) | source |
More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.