Jon Doe's picture

Jon Doe

bullpoint

·

AI & ML interests

None yet

Recent Activity

new activity 1 day ago

nvidia/Qwen3.5-397B-A17B-NVFP4:Getting nvidia/Qwen3.5-397B-A17B-NVFP4 running with SGLang (requires transformers v5) on RTX PRO 6000 (blackwell) CUDA 12.9

liked a model 2 days ago

nvidia/Qwen3.5-397B-A17B-NVFP4

new activity 5 days ago

vincentzed-hf/Qwen3.5-397B-A17B-NVFP4:Anyone try this on 4x RTX 6000 Pro yet?

View all activity

Organizations

None yet

upvoted a collection 7 days ago

Qwen3.5

2 items • Updated 5 days ago • 197

upvoted an article 7 months ago

Article

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

Aug 9, 2025

•

53

upvoted 2 collections about 1 year ago

DeepSeek R1 (All Versions)

DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated 8 days ago • 262

Llama-3.1-Nemotron-70B

SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. • 6 items • Updated about 4 hours ago • 155