Machine
RTX 3060 · Ryzen 5 5600G #adfb9365
26 runs of 14 models since Oct 20, 2026. Last run Nov 11, 2026.
26
runs
14
models
21
configs
2
configs run 2+ times
Hardware
- GPU
- NVIDIA GeForce RTX 3060 12 GB
- CPU
- AMD Ryzen 5 5600G with Radeon Graphics 6 cores
- RAM
- 30 GB
- OS
- Ubuntu 24.04.5 LTS
- Tools
- llama.cpp 26
- 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, 14 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
Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF
1 run · 1 config
model
2 runs · 2 configs
Spark-X2.6-4B-Precision-42pc
1 run · 1 config
gemma-4-E4B-it-M-TS-Q4_K_M
5 runs · 2 configs
★ bestQ4_K_Mllama.cpp16k ctxthinking default
×4 runs
72.166.6–76.6
varies
80.5 tok/s
78.8–81.9
LFM3-1.7B-BF16
1 run · 1 config
Spark-X2.6-4B-Q4_K_M
4 runs · 4 configs
Ternary-Bonsai-2-27B-Abliterated-PTQ1_0
1 run · 1 config
maritaca-ai_S5-nano-Q4_K_M
2 runs · 2 configs
LFM3-1.7B-Heretic-Abliterated-Q6_K
1 run · 1 config
S5-nano-Q8_0
1 run · 1 config
Compare with another machine
Run history
Nov 8, 2026
15:14maritaca-ai_S5-nano-Q4_K_Mllama.cpp72.3 tok/s62.814:52maritaca-ai_S5-nano-Q4_K_Mllama.cpp98.2 tok/s56.414:27S5-nano-Q8_0llama.cpp57.3 tok/s54.5Nov 2, 2026
17:16gemma-4-E4B-it-M-TS-Q4_K_M×4llama.cpp80.5 tok/s72.116:34gemma-4-E4B-it-M-TS-Q4_K_Mllama.cpp83.8 tok/s67.415:08LFM3-Omni-2B-BF16llama.cpp84.9 tok/s47.615:06LFM3-Omni-2B-Q8_0×3llama.cpp137 tok/s40.614:44LFM3-Omni-2B-Q8_0llama.cpp141 tok/s29.3Oct 30, 2026
23:35LFM3-1.7B-Heretic-Abliterated-Q6_Kllama.cpp167 tok/s61.815:12Spark-X2.6-4B-Precision-42pcllama.cpp56.0 tok/s76.5Oct 27, 2026
18:51LFM3-1.7B-BF16llama.cpp83.5 tok/s68.518:36LFM3-1.7Bllama.cpp84.3 tok/s52.018:29modelllama.cpp84.1 tok/s61.5