Phil

phil111's activity

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

New activity in google/gemma-4-26B-A4B-it about 11 hours ago

Your 260k dictionary is breaking Gemma 4's back.

#25 opened about 11 hours ago by

phil111

New activity in MiniMaxAI/MiniMax-M2.7 about 23 hours ago

This LLM is a test maxer, not a general purpose AI model.

3

#17 opened 1 day ago by

phil111

New activity in HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 4 days ago

IQ4_XS vs. Q5_K_P

6

#15 opened 4 days ago by

Data-vanOrtus

New activity in google/gemma-4-31B-it 6 days ago

Gemma 4 E4B will be as encyclopedically well-read as the 12b model?

3

#48 opened 6 days ago by

Regrin

New activity in google/gemma-4-E4B-it 7 days ago

Impressive skills for its size, but this doesn't belong on normal peoples' phones.

#10 opened 7 days ago by

phil111

New activity in google/gemma-4-26B-A4B-it 10 days ago

Gemma 4, Compared to G3, Has Notable Improvements And Regressions

5

#10 opened 11 days ago by

phil111

New activity in google/gemma-4-26B-A4B-it 11 days ago

Good Work. Please consider addressing factual hallucinations.

👍 1

3

#6 opened 12 days ago by

phil111

New activity in HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive 16 days ago

Thanks. This is by far the best denial stripping I've ever seen.

👍 3

2

#30 opened 16 days ago by

phil111

New activity in unsloth/Qwen3.5-35B-A3B-GGUF 17 days ago

More reserved settings and standard Q4_K_M still works best for me.

10

#43 opened 20 days ago by

phil111

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 21 days ago

There's got to be a better way.

23

#6 opened 24 days ago by

phil111

New activity in mistralai/Mistral-Small-4-119B-2603 25 days ago

"Small" model is now 120B and beyond the reach of most people, even in the upper-middle class with multiple consumer GPUs

❤️👍 15

68

#5 opened 29 days ago by

Fizzarolli

New activity in ServiceNow-AI/Apriel-1.5-15b-Thinker 6 months ago

Doesn't stop thinking.

👍 1

9

#3 opened 6 months ago by

phil111

New activity in zai-org/GLM-4.5 7 months ago

Impressive Broad Knowledge

👍👀 5

8

#12 opened 9 months ago by

phil111

New activity in nvidia/NVIDIA-Nemotron-Nano-9B-v2 8 months ago

This just trades general performance for domain specific gains.

🔥👍 16

11

#3 opened 8 months ago by

phil111

This just trades general performance for domain specific gains.

🔥👍 16

11

#3 opened 8 months ago by

phil111

New activity in ByteDance-Seed/Seed-OSS-36B-Base 8 months ago

Please stop blindly trusting and reporting Alibaba's scores.

👍 8

2

#1 opened 8 months ago by

phil111

New activity in google/gemma-3-270m 8 months ago

Weird responses

12

#10 opened 8 months ago by

vparth7

New activity in google/gemma-3-270m-it 8 months ago

Gemma A3B

👍 6

13

#3 opened 8 months ago by

Maria99934

New activity in openai/gpt-oss-120b 8 months ago

gpt-oss is actually good. even on less common benchmark

🤝👍 7

2

#109 opened 8 months ago by

groupfairnessllm

New activity in openai/gpt-oss-20b 8 months ago

model quality issues

5

#92 opened 8 months ago by

TheBigBlockPC