Emin Temiz PRO
etemiz
·
AI & ML interests
Alignment
Recent Activity
replied to
their
post
8 days ago
Qwen 3 numbers are in! They did a good job this time, compared to 2.5 and QwQ numbers are a lot better.
I used 2 GGUFs for this, one from LMStudio and one from Unsloth. Number of parameters: 235B A22B. The first one is Q4. Second one is Q8.
The LLMs that did the comparison are the same, Llama 3.1 70B and Gemma 3 27B.
So I took 2*2 = 4 measurements for each column and took average of measurements.
My leaderboard is pretty unrelated to others it seems. Valuable in that sense, it is another non-mainstream angle for model evaluation.
More info: https://huggingface.co/blog/etemiz/aha-leaderboard
posted
an
update
8 days ago
Qwen 3 numbers are in! They did a good job this time, compared to 2.5 and QwQ numbers are a lot better.
I used 2 GGUFs for this, one from LMStudio and one from Unsloth. Number of parameters: 235B A22B. The first one is Q4. Second one is Q8.
The LLMs that did the comparison are the same, Llama 3.1 70B and Gemma 3 27B.
So I took 2*2 = 4 measurements for each column and took average of measurements.
My leaderboard is pretty unrelated to others it seems. Valuable in that sense, it is another non-mainstream angle for model evaluation.
More info: https://huggingface.co/blog/etemiz/aha-leaderboard
Organizations
None yet
etemiz's activity
Turkish or all the languages
#1 opened 17 days ago
by
etemiz
bug free
4
#2 opened 19 days ago
by
etemiz
Larger quants please
1
1
#1 opened 9 months ago
by
YokaiKoibito
just for curiosity
9
#1 opened about 1 year ago
by
prudant
ram usage
1
#1 opened about 1 year ago
by
Tom-Neverwinter
just for curiosity
9
#1 opened about 1 year ago
by
prudant
just for curiosity
9
#1 opened about 1 year ago
by
prudant