PipelineScore
User Leaderboard

Every run. Every user.

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

Want on the board? Run the CLI.
Filter
Allalibaba|TRUNKMAINLINEFEEDERTAPDRIP|Lab-verified onlyClear filters
#User ↕Model ↕Score ↓Tier ↕
1cpu-only-prophetQwen 3 235B-A22B MoE88.8MAINLINE
2gpu-shopperQwen 2.5 72B Instruct85.1MAINLINE
3labLabQwen 3 72B Instruct85.0MAINLINE
4cpu-only-prophetQwen 2.5 72B Instruct84.8MAINLINE
5labLabQwen 3 235B-A22B MoE84.0MAINLINE
6sram-hoarderQwen 3 72B Instruct83.8MAINLINE
7inference-monkQwen 3 235B-A22B MoE83.0MAINLINE
8labLabQwen 3 32B Instruct82.4MAINLINE
9apple-siliconQwen 3 235B-A22B MoE82.3MAINLINE
10flash-attn-fanQwen 3 32B Instruct82.3MAINLINE
11mac-stackQwen 2.5 Coder 32B81.8MAINLINE
12qwen-stanQwen 3.6 72B81.6MAINLINE
13rocm-riderQwen 3 72B Instruct81.5MAINLINE
14gpt-cynicQwen 3.6 72B81.3MAINLINE
15tokenwranglerQwen 3.6 72B81.2MAINLINE
16cli-nativeQwen 3.6 72B81.1MAINLINE
17mac-stackQwen 2.5 32B Instruct81.0MAINLINE
18cli-nativeQwen 3.6 72B80.8MAINLINE
19tps-counterQwen 3 72B Instruct80.8MAINLINE
20sram-hoarderQwen 2.5 72B Instruct80.6MAINLINE
21judgementalQwen 3.6 72B80.5MAINLINE
22midnight-bencherQwen 2.5 VL 72B80.0MAINLINE
23gguf-pilgrimQwen 2.5 Coder 32B80.0MAINLINE
24labLabQwen 2.5 72B Instruct79.9MAINLINE
25quant-or-dieQwen 3 14B Instruct79.9MAINLINE
26mistral-maxiQwen 3.6 72B79.6MAINLINE
27benchmark-ratQwen 3.6 72B79.5MAINLINE
28labLabQwen 3.6 72B79.4MAINLINE
29tool-callerQwen 3.6 72B79.3MAINLINE
30one-shot-onlyQwen 3.6 72B79.1MAINLINE
31silicon-djinnQwen 3.6 72B79.1MAINLINE
32quant-or-dieQwen 3 14B Instruct79.0MAINLINE
33labLabQwen 2.5 VL 72B78.8MAINLINE
34sram-hoarderQwen 2.5 Coder 32B78.5MAINLINE
35labLabQwen 2.5 Coder 32B78.5MAINLINE
36bench-ratQwen 2.5 VL 72B77.7MAINLINE
37bench-ratQwen 3 32B Instruct77.0MAINLINE
38labLabQwen 2.5 14B Instruct76.9MAINLINE
39quant-or-dieQwen 2.5 VL 72B76.9MAINLINE
40labLabQwen 2.5 32B Instruct76.3MAINLINE
41mac-stackQwen 3 32B Instruct76.3MAINLINE
42local-llama-fanQwen 2.5 32B Instruct76.0MAINLINE
43tps-counterQwen 2.5 Coder 7B75.5MAINLINE
44local-llama-fanQwen 2.5 14B Instruct75.2MAINLINE
45mlx-mikeQwen 3 14B Instruct74.8FEEDER
46cpu-only-prophetQwen 2.5 14B Instruct74.7FEEDER
47labLabQwen 3 14B Instruct74.2FEEDER
48tps-counterQwen 2.5 32B Instruct73.9FEEDER
49rig-testerQwen 2.5 14B Instruct72.7FEEDER
50labLabQwen 3 8B Instruct72.6FEEDER
51edge-deployerQwen 3 8B Instruct71.2FEEDER
52cuda-cultQwen 2.5 7B Instruct70.8FEEDER
53labLabQwen 2.5 Coder 7B70.7FEEDER
54quant-or-dieQwen 2.5 Coder 7B70.6FEEDER
55tps-counterQwen 2.5 VL 7B70.5FEEDER
56rocm-riderQwen 2.5 VL 7B70.3FEEDER
57mlx-mikeQwen 3 8B Instruct69.5FEEDER
58cpu-only-prophetQwen 3 8B Instruct68.9FEEDER
59cuda-cultQwen 2.5 Coder 7B68.7FEEDER
60vram-monkQwen 2.5 7B Instruct66.7FEEDER
61mlx-mikeQwen 2.5 7B Instruct66.3FEEDER
62tensor-tomasQwen 2.5 VL 7B66.2FEEDER
63labLabQwen 2.5 VL 7B65.3FEEDER
64tps-counterQwen 3 4B Instruct65.2FEEDER
65labLabQwen 3 4B Instruct64.6FEEDER
66labLabQwen 2.5 7B Instruct64.4FEEDER
67cpu-only-prophetQwen 3 4B Instruct61.5FEEDER
68cuda-cultQwen 3 4B Instruct61.1FEEDER
69sram-hoarderQwen 2.5 3B Instruct59.5TAP
70local-llama-fanQwen 2.5 3B Instruct58.8TAP
71labLabQwen 2.5 3B Instruct55.1TAP
72inference-monkQwen 2.5 Coder 1.5B55.0TAP
73labLabQwen 2.5 Coder 1.5B53.8TAP
74local-llama-fanQwen 2.5 Coder 1.5B53.3TAP
75cpu-only-prophetQwen 2.5 3B Instruct52.5TAP
76apple-siliconQwen 2.5 Coder 1.5B48.4TAP
77gguf-pilgrimQwen 2.5 1.5B Instruct48.1TAP
78quant-or-dieQwen 2.5 1.5B Instruct43.8TAP
79labLabQwen 2.5 1.5B Instruct43.4TAP
80quant-or-dieQwen 2.5 1.5B Instruct43.2TAP
81gpu-shopperQwen 2.5 0.5B Instruct33.9DRIP
82vram-monkQwen 2.5 0.5B Instruct33.6DRIP
83labLabQwen 2.5 0.5B Instruct32.5DRIP
84flash-attn-fanQwen 2.5 0.5B Instruct32.2DRIP

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