whatcani.run
Home
Models
Device
Runs
Docs
GitHub
whatcani.run
Qwen
Qwen
Qwen
/
Qwen3.5-35B-A3B
35B (3B active)
February 24, 2026
Apache 2.0
Overview
Runs
Quantizations
Quant
Quantized by
Size
Decode
Prefill
Score
Actions
APEX-Compact
mudler
mudler
16.1
GB
N/A
N/A
N/A
Run
4bit
Elijah McMorris
Elijah McMorris
18.2
GB
104.0
tok/s
1,461.7
tok/s
Runs ok
Run
4bit
MLX Community
MLX Community
19.0
GB
105.1
tok/s
1,412.7
tok/s
Runs ok
Run
q4_k_m
LM Studio
LM Studio
19.7
GB
N/A
N/A
N/A
Run
q4_k_m
Unsloth
Unsloth
20.5
GB
60.1
tok/s
1,099.2
tok/s
Runs ok
Run
Device Comparison
Results include trials with
4,096
input tokens and
1,024
output tokens only.
Decode / Prefill Speeds
8 devices
All quants
M4 Max
·
36 GB
M4 Max
·
36 GB
whatcani.run
Home
Models
Device
Runs
Docs
GitHub
Login
whatcani.run