Joe
JoeSmith245
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:Disobedient and "rude" new activity
1 day ago
cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit:Nemotron 3 Super?? new activity
3 days ago
Qwen/Qwen3-Coder-Next:AWQ quantization Organizations
None yet
Disobedient and "rude"
#16 opened 1 day ago
by
JoeSmith245
Nemotron 3 Super??
1
#1 opened 1 day ago
by
JoeSmith245
AWQ quantization
๐ 1
9
#1 opened about 1 month ago
by
dr-e
AWQ? Autoround? Any ~int4 for vllm?
โ 1
3
#12 opened 4 days ago
by
JoeSmith245
unsloth for the non-gguf crowd?
๐ 1
#1 opened 5 days ago
by
JoeSmith245
chat template is broken
11
#12 opened about 1 month ago
by
grapevine-AI
2.4-2.5 bpw request?
3
#1 opened about 1 month ago
by
Michund10s9
Feb 19: Qwen3-Coder-Next GGUFs update - much better outputs!
๐ค ๐ 16
33
#5 opened about 1 month ago
by
danielhanchen
Step-3.5-Flash-W3A16-GPTQ or Step-3.5-Flash-W4A8-GPTQ ?
1
#1 opened about 1 month ago
by
Rebis
IQ2_KS model merging failed
2
#4 opened about 1 month ago
by
lan0004
Very specific json formatting issue in tool calls
โ 1
4
#14 opened about 1 month ago
by
JoeSmith245
model with thinking?
โ 2
6
#5 opened about 1 month ago
by
pypry
just curious, why the lack of <thinking> response?
3
#4 opened about 1 month ago
by
YellowjacketGames
Question about Mistral Vibe being recommended
3
#8 opened 3 months ago
by
electroglyph
Devstral for non-agentic tasks?
3
#3 opened 3 months ago
by
ooooh-nooooo
mmproj?
10
#1 opened 3 months ago
by
aaron-newsome
User/assistant message pairing broken
๐ 1
1
#3 opened 3 months ago
by
tyler94
Beware: doesn't work on compute capability 8.6, only on 8.9 and newer
๐ 1
2
#1 opened 3 months ago
by
DrRos
Does it work? Model card? Benchmarks?
#3 opened 4 months ago
by
JoeSmith245
Which template?
3
#1 opened 5 months ago
by
Topsy1