Alex Cardo

alexcardo's activity

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

New activity in google/gemma-4-31B-it 22 days ago

Incorrect output in Gemma 4: seeking a solution to the problem ( la la la )

❤️ 1

30

#79 opened 4 months ago by

Lintrarius

New activity in unsloth/gemma-4-31B-it-qat-GGUF 2 months ago

Gemma-4 QAT Special Unsloth quants

🔥 11

6

#1 opened 3 months ago by

danielhanchen

New activity in Intel/gemma-4-31B-it-int4-AutoRound 2 months ago

This quant is the best. Please conver it to GGUF

5

#7 opened 2 months ago by

alexcardo

New activity in google/gemma-4-31B-it-qat-w4a16-ct 2 months ago

Observation on Knowledge Degradation in Official QAT Quants vs. AutoRound

7

#4 opened 2 months ago by

alexcardo

New activity in google/gemma-4-31B-it-qat-w4a16-ct 3 months ago

Don't know how to delete

#2 opened 3 months ago by

alexcardo

New activity in unsloth/Qwen3.6-27B-NVFP4 3 months ago

Why is it too big?

➕ 3

9

#1 opened 3 months ago by

alexcardo

New activity in kaitchup/gemma-4-31B-it-autoround-nvfp4-all 4 months ago

Was uable to run it

#1 opened 4 months ago by

alexcardo

New activity in RedHatAI/Qwen3.6-35B-A3B-NVFP4 4 months ago

Qwen3.6-27B?

➕ 6

2

#8 opened 4 months ago by

alexcardo

New activity in Intel/gemma-4-31B-it-int4-AutoRound 4 months ago

FP4?

1

#5 opened 4 months ago by

alexcardo

Please update chat template

2

#4 opened 4 months ago by

alexcardo

New activity in google/gemma-4-31B-it 4 months ago

Infinite loop is not fixed even with Google API

👀 1

2

#63 opened 4 months ago by

alexcardo

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

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

➕ 3

20

#3 opened 5 months ago by

alexcardo

New activity in cyankiwi/gemma-4-31B-it-AWQ-8bit 4 months ago

Quant HAS issues + results with vLLM on 8x 3090

4

#1 opened 5 months ago by

dehnhaide

New activity in RedHatAI/gemma-4-31B-it-NVFP4 4 months ago

Please update tokenizer config as well

12

#2 opened 4 months ago by

alexcardo

Can you plese update the chat template

❤️ 3

1

#1 opened 4 months ago by

alexcardo

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

Is this quant support image recognition?

👍 3

11

#1 opened 4 months ago by

alexcardo

New activity in google/gemma-4-31B-it 4 months ago

Chat template is too complicated that even Gemma 4 itself has no idea how to parse it

1

#53 opened 4 months ago by

alexcardo

New activity in google/gemma-4-31B-it 5 months ago

Why Gemma4 can't recognize the entire text on image?

🚀 4

6

#12 opened 5 months ago by

alexcardo

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

这个版本对于5090单卡来说还是太大了

10

#4 opened 5 months ago by

iwaitu

New activity in Qwen/Qwen3.5-27B-GPTQ-Int4 5 months ago

30.3 GB?

👀 4

3

#6 opened 5 months ago by

pedalnomica