Alex Cardo
alexcardo
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
kaitchup/gemma-4-31B-it-autoround-nvfp4-all:Was uable to run it new activity 3 days ago
RedHatAI/Qwen3.6-35B-A3B-NVFP4:Qwen3.6-27B? new activity 8 days ago
Intel/gemma-4-31B-it-int4-AutoRound:FP4?Organizations
None yet
Was uable to run it
#1 opened 1 day ago
by
alexcardo
Qwen3.6-27B?
#8 opened 3 days ago
by
alexcardo
Please update chat template
2
#4 opened 8 days ago
by
alexcardo
Incorrect output in Gemma 4: seeking a solution to the problem ( la la la )
6
#79 opened 14 days ago
by
Lintrarius
Infinite loop is not fixed even with Google API
👀 1
2
#63 opened 25 days ago
by
alexcardo
Why is this 4bit version has a 32.7 GB size?
➕ 3
20
#3 opened about 1 month ago
by
alexcardo
Quant HAS issues + results with vLLM on 8x 3090
4
#1 opened about 1 month ago
by
dehnhaide
Please update tokenizer config as well
12
#2 opened 28 days ago
by
alexcardo
Can you plese update the chat template
❤️ 3
1
#1 opened 29 days ago
by
alexcardo
Is this quant support image recognition?
👍 2
10
#1 opened 29 days ago
by
alexcardo
Chat template is too complicated that even Gemma 4 itself has no idea how to parse it
1
#53 opened 30 days ago
by
alexcardo
Why Gemma4 can't recognize the entire text on image?
🚀 4
6
#12 opened about 1 month ago
by
alexcardo
这个版本对于5090单卡来说还是太大了
10
#4 opened about 1 month ago
by
iwaitu
30.3 GB?
👀 4
3
#6 opened about 2 months ago
by
pedalnomica
Shitty results compared to regular NVFP4 without MTP
5
#3 opened 2 months ago
by
alexcardo
怎么和fp8一样大
👍👀 21
2
#1 opened 2 months ago
by
chenzin23
Russian language support, bad grammar!
13
#12 opened 2 months ago
by
alexcardo
It doesn't translate even the example from the system prompt
1
#1 opened 10 months ago
by
alexcardo
When will it be available via API
7
#27 opened 11 months ago
by
alexcardo