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 1 day ago
IsValorum/Xing4.0-29B-A4B-APEX-I-MiniPlus-V2.1-Abliterated-GGUF:doesn't load in llama.cpp liked a model 5 days ago
basecompute/Qwen3.8-27B-BaseQuant-V1 new activity 6 days ago
meta-models/Muse-Glimmer-30B:You should make a 30B/A4B 30B/A3B (or 2B)Organizations
doesn't load in llama.cpp
1
#1 opened 1 day ago
by ZeroWw
You should make a 30B/A4B 30B/A3B (or 2B)
#69 opened 6 days ago
by ZeroWw
Please make smaller models.
❤️ 4
2
#12 opened 10 days ago
by ZeroWw
Unusable for cybersecurity because it's too censored.
#12 opened 17 days ago
by ZeroWw
Use Ling 3.0 instead of QWEN!
👍 2
1
#14 opened 18 days ago
by ZeroWw
Please release also small models: 7B/9B, ~12-/16B, ~32B
#11 opened 22 days ago
by ZeroWw
156 MB ?
1
#3 opened 24 days ago
by ZeroWw
@InclusionAI This is the way to go.
❤️ 2
#17 opened 24 days ago
by ZeroWw
Inference demo does not work.
1
#61 opened about 1 month ago
by ZeroWw
Great model, BUT it loops!
2
#13 opened about 2 months ago
by ZeroWw
Voice cloning, inflection tuning, llama.cpp
👍 1
3
#1 opened 3 months ago
by ZeroWw
broken??
2
#1 opened 3 months ago
by ZeroWw
please post also non quantized version
#16 opened 3 months ago
by ZeroWw
8B with E4B / E2B
#22 opened 3 months ago
by ZeroWw
E4B / E2B
1
#6 opened 3 months ago
by ZeroWw
Please release GLM 5.2 flash
👍 10
1
#45 opened 4 months ago
by ZeroWw
please do also gemma-4-E4B-it-qat-UD-Q4_K_XL
#1 opened 4 months ago
by ZeroWw
it does not work.
2
#1 opened 4 months ago
by ZeroWw
Can you please extract the latest 4gb version?
#1 opened 4 months ago
by ZeroWw
Very good model.
👀 1
#1 opened 4 months ago
by ZeroWw