whatcani.run
Home
Models
Device
Runs
Docs
GitHub
whatcani.run
Qwen
Qwen
Qwen
/
Qwen3.8-27B
27B
August 14, 2026
Apache 2.0
Share
Overview
Runs
Quantizations
Quant
Quantized by
Size
Decode
Prefill
Score
Actions
q4_k_s
Unsloth
Unsloth
14.3
GB
N/A
N/A
N/A
Run
nvfp4
MLX Community
MLX Community
15.0
GB
N/A
N/A
N/A
Run
4bit
MLX Community
MLX Community
15.0
GB
19.9
tok/s
197.6
tok/s
Runs poorly
Run
q4_k_s
Unsloth
Unsloth
15.0
GB
18.9
tok/s
190.9
tok/s
Runs ok
Run
8bit
MLX Community
MLX Community
27.5
GB
N/A
N/A
N/A
Run
Device Comparison
Results include trials with
4,096
input tokens and
1,024
output tokens only.
Decode / Prefill Speeds
6 devices
All quants
M4 Max
·
36 GB
M4 Max
·
36 GB
whatcani.run
Home
Models
Device
Runs
Docs
GitHub
Login
whatcani.run