Gabriel N
Gabriel31173
AI & ML interests
None yet
Recent Activity
liked a model 2 days ago
baidu/Unlimited-OCR-2 liked a Space 6 days ago
harness-hub/harness-lens liked a Space 6 days ago
joelniklaus/harness-leaderboardOrganizations
None yet
Korean document-QA results vs Qwen3.8-27B, and repetition at temperature 0 without thinking
👍 3
5
#32 opened 19 days ago
by
shoo99
New Dynamic V3.1 GGUF 512K Context Terminal Bench and DeepSWE Benchmarks!
🔥❤️ 4
3
#10 opened 14 days ago
by
danielhanchen
model file changes ??? do i need to redownlaod the weights??
1
#1 opened 15 days ago
by
pawarshardul
Nanbeige 4.3 33B - HAS NO VISION - How are you suppose to use this for WEB DEV?
👍 2
3
#21 opened 21 days ago
by
akierum
Very good and very fast
#5 opened 22 days ago
by
Gabriel31173
stock llama.cpp
➕ 5
6
#3 opened 23 days ago
by
metlov
4.05bpw thinking in other languages and/or gibberish
👀 1
5
#5 opened 2 months ago
by
khronnuz
Are these quants using Unsloth UD 3.0 or 2.0?
5
#20 opened 3 months ago
by
InfernalDread
Thinking Nightmare
🧠 2
10
#27 opened 3 months ago
by
WhiteDan64
NVFP4 support on day 0?
6
#2 opened 3 months ago
by
tuanlai001
I love you + self calibrated 6 bit?
➕ 3
1
#4 opened 3 months ago
by
Gabriel31173
Duplicate identifier results in wrong quant being pulled
1
#4 opened 3 months ago
by
Gabriel31173
Why Qwen3.8-27B overthinks? Here the reason and partial fix confirmed by benchmarks.
❤️👀 25
29
#76 opened 3 months ago
by
LuffyTheFox
Conversion script?
2
#1 opened 4 months ago
by
Gabriel31173
UD-Q8_K_XL loops
👍 1
2
#17 opened 4 months ago
by
wapxmas
llama.cpp doesn't detect the model as capable of reasoning
2
#2 opened 4 months ago
by
Gabriel31173
llama.cpp doesn't detect the model as capable of reasoning
2
#2 opened 4 months ago
by
Gabriel31173