Peter
rtzurtz
AI & ML interests
None yet
Recent Activity
new activity
about 14 hours ago
Qwen/Qwen3.5-122B-A10B:Thank you team Qwen for a 120B LLM new activity
9 days ago
Qwen/Qwen3.5-397B-A17B:Smaller GGUF without the vision weights? new activity
3 months ago
Qwen/Qwen3-Next-80B-A3B-Instruct:How much Vram needed for the full context length? Organizations
None yet
Thank you team Qwen for a 120B LLM
❤️ 2
1
#3 opened about 14 hours ago
by
rtzurtz
Smaller GGUF without the vision weights?
1
#19 opened 9 days ago
by
rtzurtz
How much Vram needed for the full context length?
6
#31 opened 5 months ago
by
Aly87
Suggesting an open-weight Gpt-Oss LLM between the 20B and 120B parameters
#156 opened 3 months ago
by
rtzurtz
230B vs 235B: Why no comparison against Qwen3-235B-A22B-Thinking-2507 ?
🤝 👍 2
7
#20 opened 4 months ago
by
rtzurtz
Are the F16 weights upcasted MXFP4? -- Why no `gpt-oss-20b-MXFP4.gguf`?
3
#34 opened 4 months ago
by
rtzurtz
Q3_K_M (112 GB) is bigger than Q3_K_XL (104 GB)?
2
#8 opened 5 months ago
by
rtzurtz
Any quants between Q8_K_XL and BF16?
1
#16 opened 7 months ago
by
rtzurtz
Good idea to remove the hybrid thinking mode
👍 4
1
#16 opened 7 months ago
by
rtzurtz
A _Q8_K_XL quant?
#4 opened 7 months ago
by
rtzurtz
MoE version with the same performance as this 32B dense
#37 opened 7 months ago
by
rtzurtz
First evaluation suggest only 14B (dense) performance?
👀 5
#33 opened 8 months ago
by
rtzurtz
Qwen is loosing broad knowledge since Qwen2.
🔥 👍 12
16
#16 opened 10 months ago
by
phil111