PipelineScore
Hardware Board

Rank the rigs.

10 hardware tags from 37 tagged runs, each ranked by the best score anyone has posted on that rig. Same testpack everywhere — the hardware is the variable. Sort by value to see score per dollar.

Your rig missing? Run the CLI with --hardware-tag and put it on the board.
10 rigs · sorted by best score (high → low) · pick any two rigs to compare
#vsHardwareBest PipelineScore ▾Best model on this rigRuns Tier
1m5-max-48gb
93.2
openai/gpt-oss-20blocal3TRUNK
2ryzen-7-7700-cpu-48gb
91.6
gpt-oss:latestlocal3TRUNK
3i7-6850k-cpu-32gb
89.5
unsloth/gemma-4-E4B-it-GGUFlocal9DRIP
4rtx-5080-16gb
87.5
qwen3.6-35b-a3blocal4MAINLINE
5m3-ultra-96gb
84.8
muse-glimmer:30blocal2MAINLINE
6rtx-5070-ti-16gb
84.2
qwen3.8-27b@iq3_xxslocal7MAINLINE
7gtx-1060-5gb-5gb
81.0
/home/thomaskyn/models/Qwen3.6-35B-A3B/Qwen3.6-35B-A3B-UD-IQ3_S.gguflocal4MAINLINE
8rtx-3070-8gb
80.9
gemma4:12b-it-qat_gpulocal1MAINLINE
9m1-16gb
77.7
qwen2.5-coder:7blocal2MAINLINE
10rx9070xt-16gb-i7-6850k-32gb-ddr4-2400
77.1
unsloth/gemma-4-E4B-it-GGUFlocal2MAINLINE
vs

Click a hardware tag to see every run on that rig; tick two rigs to go head-to-head. A rig's rank reflects its best showing, so it rewards the best model the hardware can hold. Value is score per dollar (best rig = 100) using hand-maintained street-price approximations in USD; cloud and unpriced rigs are excluded from the value ranking.