Ronen Zyroff
BigBlueWhale
·
AI & ML interests
None yet
Recent Activity
liked a model 16 days ago
moonshotai/Kimi-K3.1-Pro liked a model 27 days ago
Nanbeige/Nanbeige4.3-33BOrganizations
None yet
Harness runs Qwen 3.8 27B for 24hr on an RTX5090, installs software and writes a Postgres-SpringBoot-React spreadsheet application fully unattended
❤️ 1
3
#202 opened 2 months ago
by
anglepoiselife
Idea for a future Qwen 27B: nine 1M-token agents on one RTX 5090
1
#206 opened about 2 months ago
by
BigBlueWhale
Programmatic Sulphur-2 on RTX 5090 in 2 commands ⚡
❤️ 2
4
#22 opened 6 months ago
by
BigBlueWhale
32GiB VRAM inference using Docker- my working setup
2
#21 opened 9 months ago
by
BigBlueWhale
AWQ 4-bit produces repetitive gibberish on long outputs with vLLM v0.15.1 — root cause identified
#5 opened 10 months ago
by
BigBlueWhale
Extremely slow on 5090
9
#1 opened 11 months ago
by
STTrife
Best non-thinking model qwen ever released
👍 3
#7 opened 12 months ago
by
BigBlueWhale
Disappointment in text performance
#1 opened 12 months ago
by
BigBlueWhale
Qwen3-32B (April 2025) is superior
#2 opened 12 months ago
by
BigBlueWhale
Recommended model parameters
#5 opened about 1 year ago
by
BigBlueWhale
How about running by llama.cpp
2
#1 opened about 1 year ago
by
rosspanda0
Best open source model ever, period.
🤝 2
2
#1 opened about 1 year ago
by
BigBlueWhale
Fix prompt format in llama.cpp command
5
#2 opened about 3 years ago
by
nacs
Best open source model for coding (August 2023)
2
#1 opened about 3 years ago
by
BigBlueWhale
wizardcoder-python-34b sucks. Is this any better?
5
#1 opened about 3 years ago
by
BigBlueWhale
This model looks insanely good for coding ( 73.2 for humanEval )!
🤯👍 2
18
#1 opened about 3 years ago
by
mirek190
Uncensored my ass ....
7
#2 opened over 3 years ago
by
mirek190
Works perfectly in CPU mode with oobabooga
👍 2
5
#4 opened over 3 years ago
by
BigBlueWhale