whatcani.run
Home
Models
Device
Runs
Docs
GitHub
whatcani.run
Qwen
Qwen
Qwen
/
Qwen3-32B
32B
April 29, 2025
Apache 2.0
Share
Overview
Runs
Runs
View all benchmark runs for this model family.
Device
Quant
Runtime
Decode
Prefill
Peak memory
Date
Actions
Device
Quant
Decode
Actions
1
whatcani.run
Home
Models
Device
Runs
Docs
GitHub
Login
whatcani.run
Device
Quant
Runtime
Decode
Prefill
Peak memory
Date
Actions
M3 Ultra
28
60
256 GB
4bit
mlx_lm
0.31.1
29.6
tok/s
255.3
tok/s
20.00
GB
8%
2 months ago
M4 Max
16
40
128 GB
4bit
mlx_lm
0.31.2
18.9
tok/s
147.3
tok/s
20.00
GB
16%
2 months ago
M4 Max
16
40
128 GB
4bit
mlx_lm
0.31.2
19.1
tok/s
149.5
tok/s
20.00
GB
16%
2 months ago
Device
Quant
Decode
Actions
M3 Ultra
28
60
256 GB
4bit
29.6
tok/s
M4 Max
16
40
128 GB
4bit
18.9
tok/s
M4 Max
16
40
128 GB
4bit
19.1
tok/s
1