PipelineScore
User Leaderboard

Every run. Every user.

25 submissions from 50 users. Sort, filter, find someone who ran your model.

Want on the board? Run the CLI.
Filter
Allalibababigcodecognitivecomputationscommunitydeepseekgooglehuggingfaceibmmetamicrosoftmistralopenchattiiyi|TRUNKMAINLINEFEEDERTAPDRIP|Lab-verified only|rig: rtx-3060-12gb ✕Clear filters
#User ↕Model ↕Score ↑Tier ↕
1bench-ratSmolLM 1.7B
29.0
DRIP
2quant-or-dieTinyLlama 1.1B Chat
29.6
DRIP
3cpu-only-prophetSmolLM2 1.7B
42.1
TAP
4vram-monkGranite 3.1 2B Instruct
46.5
TAP
5gpu-shopperStarCoder2 3B
49.5
TAP
6local-llama-fanGemma 2 2B IT
51.2
TAP
7cpu-only-prophetQwen 2.5 3B Instruct
52.5
TAP
8local-llama-fanQwen 2.5 Coder 1.5B
53.3
TAP
9midnight-bencherLlama 3.2 3B Instruct
54.4
TAP
10inference-monkStarCoder2 7B
56.7
TAP
11cpu-only-prophetMistral 7B Instruct v0.3
59.4
TAP
12local-llama-fanYi 1.5 6B Chat
61.1
FEEDER
13cpu-only-prophetQwen 3 4B Instruct
61.5
FEEDER
14cpu-only-prophetYi 1.5 9B Chat
62.6
FEEDER
15edge-deployerFalcon Mamba 7B
62.8
FEEDER
16rocm-riderOpenChat 3.6 8B
63.0
FEEDER
17rocm-riderDolphin 3.0 Llama 3.1 8B
63.7
FEEDER
18cuda-cultGemma 2 9B IT
66.8
FEEDER
19apple-siliconYi Coder 9B
68.1
FEEDER
20cpu-only-prophetQwen 3 8B Instruct
68.9
FEEDER
21edge-deployerPhi 4 14B
69.3
FEEDER
22mac-stackDeepSeek R1 Distill Llama 8B
69.5
FEEDER
23vram-monkLlama 4 8B Instruct
71.0
FEEDER
24mlx-mikeQwen 3 14B Instruct
74.8
FEEDER
25local-llama-fanQwen 2.5 14B Instruct
75.2
MAINLINE

Top reviewers

By best PipelineScore submitted. Click a user to open their dashboard.

#1
lab
96 runs
89.5
#2
cpu-only-prophet
17 runs
88.8
#3
flash-attn-fan
17 runs
88.1
#4
rig-tester
15 runs
86.6
#5
mac-stack
21 runs
86.0
#6
quant-or-die
18 runs
85.3
#7
gpu-shopper
12 runs
85.1
#8
local-llama-fan
15 runs
84.8
#9
inference-monk
15 runs
84.7
#10
bench-rat
12 runs
84.5
#11
deepseek-wins
1 run
84.0
#12
sram-hoarder
11 runs
83.8
← Switch to model leaderboard