Daniel Dias Rodrigues
nerun
·
AI & ML interests
None yet
Recent Activity
updated a model about 16 hours ago
nerun/PentaCoder-9B-i1-MTP-GGUF published a model about 19 hours ago
nerun/PentaCoder-9B-i1-MTP-GGUF new activity about 21 hours ago
pragmaticcs/PentaCoder-9B-i1-GGUF:MTP?Organizations
None yet
RTX 3080 10GB MTP A/B: Q4_K_M 93.6 → 133.3 tok/s at n-max=2
1
#8 opened 3 months ago
by
SG0101
Q5 quants?
#10 opened 6 days ago
by
nerun
Qwen3.8-9B someday?
👀👍 9
1
#237 opened 6 days ago
by
nerun
No Speed Increase on an MBP M3 Pro 36 GB
👍 4
5
#22 opened 5 months ago
by
vbot
top_k and min_p
#10 opened 8 days ago
by
nerun
MTP someday?
4
#6 opened 12 days ago
by
nerun
VL 2B vs 1.7B
1
#6 opened 11 days ago
by
nerun
LFM3-8B-A1B?
🚀 2
3
#40 opened 12 days ago
by
nerun
Memory needed per quant at 8K context (file sizes + KV estimate)
👍👀 3
5
#2 opened 17 days ago
by
localllmrig
MTP?
🔥 4
6
#1 opened 19 days ago
by
qquver
LFM2.5-24B-A2B vs Qwen3.6-35B-A3B in 5 physics simulation challenges
👍 2
6
#7 opened 26 days ago
by
Higen
How to control thinking level ?
2
#37 opened 11 months ago
by
kalashshah19
Great but some loops
🔥 5
1
#3 opened 3 months ago
by
Miltos22
Performance report on RX 6600 M
1
#9 opened about 2 months ago
by
nerun
Incredible, thank you
#1 opened about 2 months ago
by
nerun
MTP not working
2
#19 opened about 2 months ago
by
nerun
Performance report with guide to help others
🤝🔥 1
#5 opened about 2 months ago
by
nerun
Q4 fails as an AI Agent, but Q5 rocks!
1
#8 opened 2 months ago
by
nerun