Machine
RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt · Ryzen 5 5600 #aed0cdfe
6 runs of 5 models since Aug 24, 2026. Last run Aug 24, 2026.
6
runs
5
models
5
configs
1
configs run 2+ times
Hardware
- GPU
- AMD Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT 11 GB
- CPU
- AMD Ryzen 5 5600 6-Core Processor 6 cores
- RAM
- 15 GB
- OS
- CachyOS
- Tools
- LM Studio 5 · vLLM 1
- Client
- 0.4.40
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, 5 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
Ornith-1.5-9B-MTP-Q6_K
1 run · 1 config
Ornith-1.5-9B-MTP-Q6_0_ROCMFPX_AGENT
1 run · 1 config
Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENT
2 runs · 1 config
★ bestQ4_0LM Studio8k ctxthinking default
×2 runs
57.757.0–58.4
steady
58.3 tok/s
57.3–59.3
Ornith-1.5-9B-MTP-IQ4_XS
1 run · 1 config
Qwen3.8-27B-ROCMFP2
1 run · 1 config
Compare with another machine
Run history
Aug 24, 2026
12:44Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENTLM Studio59.3 tok/s58.412:38Ornith-1.5-9B-MTP-Q6_KLM Studio44.4 tok/s76.712:16Ornith-1.5-9B-MTP-Q6_0_ROCMFPX_AGENTLM Studio34.2 tok/s66.412:06Ornith-1.5-9B-MTP-IQ4_XSLM Studio50.8 tok/s56.111:57Ornith-1.5-9B-MTP-Q4_0_ROCMFP4_COHERENTLM Studio57.3 tok/s57.011:18Qwen3.8-27B-ROCMFP2vLLM5167 tok/s0.0