LilaRest

LilaRest's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in LilaRest/gemma-4-31B-it-NVFP4-turbo 5 months ago

differently from original gemma 4 31b model, the turboquant version is not working with roo code

6

#10 opened 5 months ago by

colevr

Mlx Native multimodal and text only variants please

1

#7 opened 5 months ago by

Narutoouz

Error using your recommended docker

3

#5 opened 5 months ago by

robinsyihab

Is this quant support image recognition?

👍 3

11

#1 opened 5 months ago by

alexcardo

model with opencode & claude code

5

#4 opened 5 months ago by

soslowboy100

Updated Chat Template

1

#3 opened 5 months ago by

faheemraza1

New activity in nvidia/Gemma-4-31B-IT-NVFP4 5 months ago

This model wasn't trained with FP4 or NVFP4

2

#8 opened 5 months ago by

yangus87

Why is this 4bit version has a 32.7 GB size?

➕ 3

20

#3 opened 6 months ago by

alexcardo

New activity in LilaRest/gemma-4-31B-it-NVFP4-turbo 5 months ago

Just squeeze 4-5 GB more.

2

#2 opened 5 months ago by

emircanerkul

Is this quant support image recognition?

👍 3

11

#1 opened 5 months ago by

alexcardo

New activity in nvidia/Gemma-4-31B-IT-NVFP4 5 months ago

Why is this 4bit version has a 32.7 GB size?

➕ 3

20

#3 opened 6 months ago by

alexcardo

New activity in nvidia/Gemma-4-31B-IT-NVFP4 6 months ago

Why is this 4bit version has a 32.7 GB size?

➕ 3

20

#3 opened 6 months ago by

alexcardo