whatcani.run
Home
Models
Device
Runs
Docs
GitHub
whatcani.run
Qwen
Qwen
Qwen
/
Qwen3.5-27B
27B
February 24, 2026
Apache 2.0
Overview
Runs
Quantizations
Quant
Quantized by
Size
Decode
Prefill
Score
Actions
4bit
MLX Community
MLX Community
15.0
GB
N/A
N/A
N/A
Run
q4_k_m
Unknown
15.4
GB
N/A
N/A
N/A
N/A
q4_k_m
Unsloth
Unsloth
15.6
GB
17.3
tok/s
189.3
tok/s
Runs poorly
Run
q6_k
Unsloth
Unsloth
20.9
GB
14.2
tok/s
191.2
tok/s
Runs poorly
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
9 devices
All quants
M4 Max
·
36 GB
M4 Max
·
36 GB
whatcani.run
Home
Models
Device
Runs
Docs
GitHub
Login
whatcani.run