whatcani.run
Home
Models
Device
Runs
Docs
GitHub
whatcani.run
Qwen
Qwen
Qwen
/
Qwen3-Coder-Next
80B (3B active)
January 30, 2026
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
M4 Max
16
40
128 GB
4bit
mlx_lm
0.31.2
77.3
tok/s
1,012.2
tok/s
45.00
GB
35%
1 month ago
M1 Ultra
20
48
64 GB
4bit
mlx_lm
0.31.2
47.1
tok/s
648.5
tok/s
45.00
GB
70%
2 months ago
M4 Max
16
40
128 GB
4bit
mlx_lm
0.31.2
80.4
tok/s
1,311.4
tok/s
45.00
GB
35%
2 months ago
M4 Pro
14
20
64 GB
4bit
mlx_lm
0.31.2
65.3
tok/s
573.3
tok/s
43.00
GB
67%
2 months ago
M4 Pro
14
20
64 GB
q4_k_m
llama.cpp
b8793
39.4
tok/s
469.7
tok/s
28.74
GB
45%
2 months ago
Device
Quant
Decode
Actions
M4 Max
16
40
128 GB
4bit
77.3
tok/s
M1 Ultra
20
48
64 GB
4bit
47.1
tok/s
M4 Max
16
40
128 GB
4bit
80.4
tok/s
M4 Pro
14
20
64 GB
4bit
65.3
tok/s
M4 Pro
14
20
64 GB
q4_k_m
39.4
tok/s
1