Qwen3.6-27B
Collection
10 items • Updated • 5
crazyi
crazyi
·
AI & ML interests
None yet
Recent Activity
new activity 4 days ago
deepreinforce-ai/Ornith-1.0-35B:MTP layers upvoted a collection 3 months ago
Qwen3.6-27B new activity 3 months ago
deepsweet/Qwen3.6-27B-MLX-oQ8-FP16:Is there a benchmark comparison between DFLASH and native MTP?Organizations
None yet
MTP layers
1
#26 opened 18 days ago
by 
Treene
upvoted a collection 3 months ago
Is there a benchmark comparison between DFLASH and native MTP?
3
#3 opened 3 months ago
by crazyi
liked a
model 3 months ago
The original Qwen3.6-27B is multimodal
8
#1 opened 3 months ago
by crazyi
updated 4
models 3 months ago
crazyi/Qwopus3.6-27B-v1-preview-mlx-8bit
Text Generation • 27B • Updated • 8
crazyi/Qwen3.5-27B-GLM5.1-v1-mlx-8bit
Text Generation • 27B • Updated • 160
crazyi/Qwopus3.5-27B-v3.5-mlx-8bit
Text Generation • 27B • Updated • 14 • 1
crazyi/Qwopus3.5-0.8B-v3-mlx-8bit
Text Generation • 0.2B • Updated • 12
Why is there a 4k ctx limit?
2
#7 opened 3 months ago
by crazyi
liked a
model 3 months ago
I used it on Omlx,but it showed thinking as content.
3
#4 opened 3 months ago
by 
BeCreated
What is the difference between this and the original Qwen3.6-27B?
1
#1 opened 3 months ago
by crazyi
published 4
models 3 months ago
crazyi/Qwopus3.6-27B-v1-preview-mlx-8bit
Text Generation • 27B • Updated • 8
crazyi/Qwen3.5-27B-GLM5.1-v1-mlx-8bit
Text Generation • 27B • Updated • 160
crazyi/Qwopus3.5-0.8B-v3-mlx-8bit
Text Generation • 0.2B • Updated • 12
crazyi/Qwopus3.5-27B-v3.5-mlx-8bit
Text Generation • 27B • Updated • 14 • 1
Can you please share a mlx version for this 0.8b
2
#1 opened 3 months ago
by crazyi
Is there a problem with the model's size?
#3 opened 4 months ago
by crazyi
Is there a plan to release an MLX version of 8bit?
1
#1 opened 4 months ago
by crazyi