Robert Sinclair
ZeroWw
AI & ML interests
LLMs optimization (model quantization and back-end optimizations) so that LLMs can run on computers of people with both kidneys. Discord: https://discord.com/channels/@robert_46007
Recent Activity
new activity about 10 hours ago
Qwen/Qwen3.6-27B:When will QWEN 3.6 MAX be released? upvoted a collection about 10 hours ago
Qwen3.6 upvoted a collection about 10 hours ago
Qwen3.5Organizations
When will QWEN 3.6 MAX be released?
👍 1
#32 opened about 10 hours ago
by ZeroWw
Please make also smaller models like 32B or 8B-16B
👍 13
1
#14 opened 29 days ago
by ZeroWw
Possibility of Open Sourcing Grok-2 Mini?
➕ 34
11
#5 opened 9 months ago
by 
ConicCat
Grok 3 release time?
➕ 1
5
#44 opened 4 months ago
by ZeroWw
Voice cloning error.
#1 opened 5 months ago
by ZeroWw
I find qwen3 next exceptional, but too big.
1
#7 opened 6 months ago
by ZeroWw
In the face of google who didn't release old gemini! (Thanks)
👍 15
13
#21 opened 9 months ago
by ZeroWw
Request: Smaller models.
🔥➕ 9
2
#33 opened 8 months ago
by ZeroWw
Thinking but no solution?
5
#54 opened 9 months ago
by ZeroWw
Absurd sizes.
4
#12 opened 9 months ago
by ZeroWw
Model does *NOT* work.
👍 1
3
#1 opened 9 months ago
by ZeroWw
you should try this.
#8 opened 10 months ago
by ZeroWw
ZeroGPU Assertion ERROR
2
#6 opened 10 months ago
by ZeroWw
Fully opensource?
2
#2 opened 10 months ago
by ZeroWw
Some intermediate models would be nice.
#4 opened 10 months ago
by ZeroWw
Not working for me.
2
#5 opened 11 months ago
by ZeroWw
Can you please release how you post-train qwen3 on deepseek?
2
#12 opened 11 months ago
by ZeroWw
Please create also 4B and 8B models
#6 opened 12 months ago
by ZeroWw
This one works.
#1 opened 12 months ago
by ZeroWw
GGUF model with architecture gemma3 is not supported yet
3
#2 opened about 1 year ago
by 
kieransmith