Josh Leverette
coder543
AI & ML interests
LLMs
Recent Activity
new activity about 4 hours ago
LiquidAI/LFM2.5-2.6B-GGUF:QAD Q4_K_M? new activity 1 day ago
inclusionAI/Ling-3.0-tiny:MTP support? new activity 2 days ago
noctrex/Ling-3.0-tiny-MXFP4_MOE-GGUF:MTP seems to be missing?Organizations
None yet
QAD Q4_K_M?
#8 opened about 4 hours ago
by
coder543
MTP support?
➕ 5
#11 opened 1 day ago
by
coder543
MTP seems to be missing?
2
#1 opened 2 days ago
by
coder543
New GGUFs required? "chat : add new template for DeepSeek V4 Flash 0731 (#26398)"
👍 4
5
#28 opened 16 days ago
by
rtzurtz
Thanks for the release!
❤️ 7
1
#1 opened 20 days ago
by
coder543
1-bit Kimi K3 vs Claude Opus 5 vs GPT 5.6
👀🚀 20
24
#12 opened 21 days ago
by
danielhanchen
Upstream the `laguna` branch?
➕ 1
2
#19 opened 22 days ago
by
coder543
DFlash configuration issue causing acceptance rate collapse
👍 7
2
#6 opened 29 days ago
by
coder543
LFM2.5-230M beats LFM2.5-350M on GSM8K?
👀 1
2
#10 opened about 2 months ago
by
coder543
Chat template that supports reasoning
5
#1 opened 2 months ago
by
coder543
Chat template issues with multiple rounds of tool calling
➕ 2
11
#115 opened 3 months ago
by
Kimahriman
GGUF advertises wrong max context?
6
#2 opened 3 months ago
by
coder543
Context length is at 131k instead of 256k
5
#8 opened 3 months ago
by
Orangeswim
Wrong context size in config.json?
👍 1
1
#10 opened 3 months ago
by
coder543
Benchmarks of reasoning levels?
1
#6 opened 3 months ago
by
coder543
correct max context length to 200k
1
#1 opened 3 months ago
by
walterbm-cohere
mmproj file?
5
#1 opened 3 months ago
by
Grossor
Maximum duration in one input?
👀 1
5
#3 opened 4 months ago
by
coder543
Qwen3.5 support
🤝 1
1
#1 opened 4 months ago
by
coder543
Eagle model
➕ 2
2
#3 opened 5 months ago
by
sulpher