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
updated a model about 9 hours ago
ZeroWw/MiniCPM-V-4_7-35B-A3B-IQ3_XXS.gguf published a model about 9 hours ago
ZeroWw/MiniCPM-V-4_7-35B-A3B-IQ3_XXS.gguf new activity about 12 hours ago
openbmb/MiniCPM-V-4.7-35B-A3B-gguf:2x slower than qwen 3.6 35b A3BOrganizations
2x slower than qwen 3.6 35b A3B
1
#12 opened about 12 hours ago
by ZeroWw
Please add also: iq3_xxs quant
#11 opened about 12 hours ago
by ZeroWw
Please publish the method you used.
#2 opened about 18 hours ago
by ZeroWw
Please try the same with Qwen 35B A3B
#1 opened 1 day ago
by ZeroWw
Please do the same with qwen 35B A3B
#6 opened 1 day ago
by ZeroWw
With a temp of 0.7 there are still refusals.
#1 opened 1 day ago
by ZeroWw
Finetuning code release
➕ 1
2
#8 opened 6 days ago
by 
kaivoss
Quantized with imatrix.
#9 opened 2 days ago
by ZeroWw
You should try the same on LING 3.0 tiny
👀 1
2
#1 opened 6 days ago
by ZeroWw
Please publish the IMATRIX
#21 opened 2 days ago
by ZeroWw
Tnanks for this.
❤️ 1
#1 opened 3 days ago
by ZeroWw
Please also do the iq3_xxs quant
#1 opened 4 days ago
by ZeroWw
Please, make also 27B A3B !
👍 10
#238 opened 4 days ago
by ZeroWw
Please, make also 27B A3B !
#139 opened 4 days ago
by ZeroWw
Great release! Please make also small ones. like 27B/A3B or 9B or something like that
➕ 17
8
#4 opened 5 days ago
by ZeroWw
How does it compare to Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS.gguf ?
1
#2 opened 10 days ago
by ZeroWw
This is great, please do also the normal one
2
#20 opened 11 days ago
by ZeroWw
Benchmarked Cyber-Tiel-Coder-35B-A3B-UD-IQ4_XS.gguf
❤️🔥 3
2
#6 opened 15 days ago
by 
userr99
Can you try to do the same with gemma 26 a4b ?
#7 opened 12 days ago
by ZeroWw