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
published a model about 7 hours ago
Myric/abliteration-token-efficiency-study updated a model about 7 hours ago
Myric/abliteration-token-efficiency-study updated a model 2 days ago
Myric/Qwen3.6-35B-A3B-APEX-GGUFOrganizations
None yet
Lightning is really efficient
#1 opened 4 days ago
by Myric
Quants wrong?
5
#2 opened 5 days ago
by 
CNWPlayer
pytorch imatrix
1
#2 opened 5 days ago
by 
rahul7star
Coding benchmark: APEX-i-quality avoided thinking loops
3
#7 opened 6 days ago
by 
LantaldeMikel
Error on loading I-Quality model
2
#1 opened 9 days ago
by 
Emerald7664
Novel APEX Quant of Moonshot 16B model
2
#1 opened 27 days ago
by Myric
brywil/llama.cpp executable
1
#2 opened 10 days ago
by 
Andy5k
MTP Heads
❤️ 6
4
#25 opened 11 days ago
by Myric
nice quants
3
#1 opened 11 days ago
by 
pawarshardul
Context size!!
3
#1 opened 12 days ago
by 
dwadaadadqq
Run on CPU?
11
#1 opened 12 days ago
by rahul7star
Running on a CPU
#1 opened 12 days ago
by Myric
Comparisson to other quants
#4 opened 17 days ago
by Myric
dflash drafter model load failure (on dflash q4_k or q8_0)
1
#6 opened 18 days ago
by 
dilavni
Tiny MoE from IBM with tool calling
#1 opened 18 days ago
by Myric
I-matrix Dataset
6
#4 opened 21 days ago
by 
resynth
Smallest native 1m context model I've seen. I'd compare it to Haiku.
#2 opened 22 days ago
by Myric
Issues with Laguna and openclaw
3
#3 opened 22 days ago
by 
scottgl
This actually works!
❤️👀 4
1
#1 opened 23 days ago
by 
danielcherubini
Novel APEX Quant of Laguna-S-2.1 (agentic coding, DFlash)
9
#1 opened 24 days ago
by Myric