Marshall Belles
Bellesteck
AI & ML interests
None yet
Recent Activity
liked a model 29 days ago
biMEMO/Qwen3.8-27B-int4-AutoRound new activity 29 days ago
RedHatAI/gemma-4-12B-it-NVFP4:Recipe ideas liked a model 29 days ago
biMEMO/Ornith-1.5-35B-A3B-int4-AutoRound-MTPOrganizations
None yet
Recipe ideas
2
#2 opened about 1 month ago
by
xdavxd
Friggin AWESOME quant of a GREAT model.
👍❤️ 6
3
#2 opened about 1 month ago
by
Bellesteck
3.8 27b variant?
1
#7 opened about 2 months ago
by
jbolle
Error: Context length exceeded (13,219 tokens). Cannot compress further.
4
#12 opened 3 months ago
by
dbrzezinsky
[Fixed] Chat template + Tool Calling Fix
❤️🤝 2
8
#11 opened 3 months ago
by
Bellesteck
Does not perform well
🤗❤️ 2
2
#1 opened 4 months ago
by
Hypersniper
Thanks - it works well in opencode
🤝❤️ 7
13
#1 opened 4 months ago
by
Milor123
16Gb VRAM not enough even for small context
16
#10 opened 5 months ago
by
redval
Vision support
4
#11 opened 5 months ago
by
prashanthellina
Broken chat_template tool calling and thinking
14
#9 opened 5 months ago
by
livepeer-ren
Weirdly no perf gain
5
#1 opened 6 months ago
by
Orosius
HOLY $#!T...
❤️🚀 4
2
#1 opened 6 months ago
by
Bellesteck
Tool call doesn't work in this model and v2 too
1
#6 opened 6 months ago
by
havenoammo
Original model taken down?
3
#1 opened 6 months ago
by
Bellesteck
Cannot summarize 8000 tokens
2
#22 opened 10 months ago
by
kalle07
Question regarding the FP8 version
1
#9 opened 10 months ago
by
thecr7guy
Fast Start - Docker Compose
🚀👍 2
1
#3 opened 10 months ago
by
Bellesteck
Tool Calling (jinja template) Issues
14
#1 opened about 1 year ago
by
Bellesteck
Great Quant!
🔥 1
5
#1 opened about 1 year ago
by
Bellesteck
Serve with vLLM
5
#1 opened about 1 year ago
by
faheemraza1