whatcani.run
Home
Models
Device
Runs
Docs
GitHub
whatcani.run
Qwen
Qwen
Qwen
/
Qwen3-4B-Instruct-2507
4B
August 5, 2025
Apache 2.0
Overview
Runs
Runs
View all benchmark runs for this model family.
Device
Quant
Runtime
Decode
Prefill
Peak memory
Date
Device
Quant
Decode
Actions
1
whatcani.run
Home
Models
Device
Runs
Docs
GitHub
Login
whatcani.run
Device
Quant
Runtime
Decode
Prefill
Peak memory
Date
M3
8
10
24 GB
q8_0
llama.cpp
b8480
11.2
tok/s
234.0
tok/s
0.71
GB
3%
3 weeks ago
M1 Max
10
32
64 GB
q8_0
llama.cpp
b8240
30.4
tok/s
495.6
tok/s
5.02
GB
8%
3 weeks ago
M1 Max
10
32
64 GB
4bit
mlx_lm
0.31.0
39.9
tok/s
290.2
tok/s
4.08
GB
6%
3 weeks ago
Device
Quant
Decode
Actions
M3
8
10
24 GB
q8_0
11.2
tok/s
M1 Max
10
32
64 GB
q8_0
30.4
tok/s
M1 Max
10
32
64 GB
4bit
39.9
tok/s
1