Machine
Advanced Micro Devices Inc Ati Hawkpoint1 · Ryzen 7 H 255 w/ Radeon 780M Graphics #55a8f2cc
16 runs of 8 models since Nov 15, 2026. Last run Nov 21, 2026.
16
runs
8
models
10
configs
3
configs run 2+ times
Hardware
- GPU
- Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 32 GB
- CPU
- AMD Ryzen 7 H 255 w/ Radeon 780M Graphics 8 cores
- RAM
- 14 GB
- OS
- Ubuntu 26.04.1 LTS
- Tools
- llama.cpp 16
- Client
- 0.4.99
Models on this machine
One dot per model, at its best config. Up is better answers, right is faster. Time to finish counts every token the model wrote, thinking included, so a model that talks a lot ends up further left.
Best trade-off: quality 60+, and nothing else here is both faster and betterOther models · dot size = number of runs
Medians of each model's best config, 8 models.
Best config per model
sort
Runs with the same model, quant, tool, context, thinking and KV cache count as one config. Numbers are the median of its runs, and each dot is one run on the 0–100 quality scale. ★ marks the best config with at least 2 rated runs.
configrunsqualityeach runspeed
Qwen3.8-27B-GSQ-RCO-Intel-Arc-Tuned-MTP-3.7BPW
1 run · 1 config
Qwen3.8-27B-GSQ-RCO-Intel-Arc-Tuned-MTP-3.2BPW
4 runs · 2 configs
★ bestllama.cpp128k ctxthinking oneffort xhigh
×3 runs
84.883.1–85.2
steady
19.0 tok/s
18.4–19.2
Ornith-1.5-9B-MTP-Q8_0
1 run · 1 config
Swift-1.5-Ornith-9B-Q8_0
1 run · 1 config
LFM2.5-24B-A2B-QAD-Q4_0
1 run · 1 config
gemma-4-26B-A4B-it-qat-UD-Q4_K_XL
6 runs · 2 configs
★ bestQ4_Kllama.cpp128k ctxthinking on
×3 runs
70.568.4–74.3
steady
30.0 tok/s
25.0–30.3
LFM2.5-24B-A2B-QAD-Q2_K_L
1 run · 1 config
LFM3-Omni-2B-Q8_0
1 run · 1 config
Compare with another machine
Run history
Nov 21, 2026
19:29gemma-4-26B-A4B-it-qat-UD-Q4_K_XLllama.cpp31.7 tok/s62.119:06LFM2.5-24B-A2B-QAD-Q4_0llama.cpp64.9 tok/s75.918:43LFM2.5-24B-A2B-QAD-Q2_K_Lllama.cpp65.7 tok/s59.418:23LFM3-Omni-2B-Q8_0llama.cpp115 tok/s42.5Nov 15, 2026
21:48Qwen3.8-27B-GSQ-RCO-Intel-Arc-Tuned-MTP-3.2BPWllama.cpp10.0 tok/s82.012:46gemma-4-26B-A4B-it-qat-UD-Q4_K_XLllama.cpp25.0 tok/s74.311:54gemma-4-26B-A4B-it-qat-UD-Q4_K_XL×2llama.cpp32.5 tok/s71.810:40gemma-4-26B-A4B-it-qat-UD-Q4_K_XL×2llama.cpp30.2 tok/s69.509:57Swift-1.5-Ornith-9B-Q8_0llama.cpp32.1 tok/s80.009:04Ornith-1.5-9B-MTP-Q8_0llama.cpp31.2 tok/s84.204:38Qwen3.8-27B-GSQ-RCO-Intel-Arc-Tuned-MTP-3.2BPW×3llama.cpp19.0 tok/s84.8