Machine
RTX 2060 · Ryzen 7 4800H #f6621756
11 runs of 10 models since Sep 21, 2026. Last run Nov 10, 2026.
11
runs
10
models
10
configs
1
configs run 2+ times
Hardware
- GPU
- NVIDIA GeForce RTX 2060 6 GB
- CPU
- AMD Ryzen 7 4800H with Radeon Graphics 8 cores
- RAM
- 31 GB
- OS
- Windows 11 Home 26H2
- Tools
- llama.cpp 9 · OpenAI-compatible 2
- 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, 10 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
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2.1-Abliterated-GGUF:ABLITERATED
1 run · 1 config
openbmb/MiniCPM-V-4.7-35B-A3B-gguf
1 run · 1 config
LiquidAI/LFM2.5-24B-A2B-GGUF
1 run · 1 config
IsValorum/Cyber-Tiel-Coder-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:1
1 run · 1 config
IsValorum/Flint-APEX-I-MiniPlus-V2.1-GGUF:1
1 run · 1 config
JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF
2 runs · 1 config
★ bestQ4_K_Mllama.cpp64k ctxthinking default
×2 runs
63.362.3–64.4
steady
15.6 tok/s
14.7–16.4
peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF
1 run · 1 config
peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF
1 run · 1 config
inclusionAI/Ling-3.0-tiny-GGUF
1 run · 1 config
ItachiSan/LiquidCode-2.5-24B-A2B-GGUF
1 run · 1 config
Compare with another machine
Run history
Nov 4, 2026
17:30LiquidCode-2.5-24B-A2B-GGUF:Q4_K_Mllama.cpp26.0 tok/s38.116:19LFM2.5-24B-A2B-GGUF:Q4_0llama.cpp23.6 tok/s78.8Oct 5, 2026
18:14Cyber-Tiel-Coder-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:1llama.cpp18.1 tok/s77.117:14Occamy-1.0-APEX-I-MiniPlus-V2.1-Abliterated-GGUF:ABLITERATEDllama.cpp17.1 tok/s81.9