Bryan Harris
Myric
AI & ML interests
I'm interested in running models on hardware I have rather than hardware I can rent (Or maybe in addition to hardware I can rent.)
Recent Activity
updated a model 6 days ago
Myric/apex-quant-benchmarks updated a model 7 days ago
Myric/Flint-APEX-GGUF published a model 7 days ago
Myric/Flint-APEX-GGUFOrganizations
None yet
Benchmarks of my models
#1 opened 14 days ago
by Myric
Vision file?
2
#2 opened about 2 months ago
by 
ItachiSan
GuideLines to Run on RTX 3060 12 GB with LLama.cpp Needed
1
#3 opened 2 months ago
by 
SolutionsDealer
DGX Spark llama-server 30+ tokens/second configuration
2
#5 opened 3 months ago
by 
msamon
Why Q3_K for ssm.apha/beta?
11
#2 opened 3 months ago
by 
anjeysapkovski
thank you
2
#8 opened 3 months ago
by 
echalupa
Lightning is really efficient
👍 3
#1 opened 3 months ago
by Myric
Quants wrong?
5
#2 opened 3 months ago
by 
CNWPlayer
pytorch imatrix
1
#2 opened 3 months ago
by 
rahul7star
Coding benchmark: APEX-i-quality avoided thinking loops
3
#7 opened 3 months ago
by 
LantaldeMikel
Error on loading I-Quality model
2
#1 opened 3 months ago
by 
Emerald7664
Novel APEX Quant of Moonshot 16B model
2
#1 opened 4 months ago
by Myric
brywil/llama.cpp executable
1
#2 opened 3 months ago
by 
Andy5k
MTP Heads
❤️ 6
4
#25 opened 3 months ago
by Myric
nice quants
3
#1 opened 3 months ago
by 
pawarshardul
Context size!!
3
#1 opened 3 months ago
by 
dwadaadadqq
Run on CPU?
11
#1 opened 3 months ago
by rahul7star
Running on a CPU
#1 opened 3 months ago
by Myric
Comparisson to other quants
#4 opened 3 months ago
by Myric
dflash drafter model load failure (on dflash q4_k or q8_0)
1
#6 opened 3 months ago
by 
dilavni