lostmsu

lostmsu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in prefeitura-rio/Rio-3.5-Open-397B 4 months ago

mxfp4 QAT variant

#12 opened 4 months ago by

lostmsu

New activity in google/gemma-4-12B-it-qat-q4_0-gguf 4 months ago

Can thinking be toggled per response in a multi-turn conversation?

5

#2 opened 4 months ago by

lostmsu

New activity in bartowski/Qwen_Qwen3.5-27B-GGUF 7 months ago

Was Q8_0 quantized from original model or is it a copy of -FP8 variant?

1

#3 opened 7 months ago by

lostmsu

New activity in lmstudio-community/Qwen3.5-27B-GGUF 7 months ago

Is Q8_0 requantized from original model or simply a copy of FP8?

#4 opened 7 months ago by

lostmsu

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF about 1 year ago

Is the Q8_0 derived from the official FP8?

1

#13 opened about 1 year ago by

lostmsu

New activity in HROMEK-Industries/HROM-M1 over 1 year ago

Any benchmarks on public datasets?

1

#1 opened over 1 year ago by

lostmsu

New activity in bartowski/Meta-Llama-3.1-8B-Instruct-GGUF almost 2 years ago

Meta-Llama-3.1-8B-Instruct-bf16.gguf is still old version?

5

#4 opened about 2 years ago by

Firepin