Jan Reges

janreges3's activity

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

New activity in unsloth/Qwen3.6-27B-NVFP4 17 days ago

NVFP4 vs FP8 throughput on an RTX 6000 Pro 96 GB (Blackwell) - real vLLM numbers

❤️👍 3

2

#9 opened 17 days ago by

janreges3

liked a model 18 days ago

lovedheart/Qwen-AgentWorld-35B-A3B-FP8

Text Generation • 35B • Updated Jun 25 • 12.7k • 1

New activity in nvidia/Qwen3.6-27B-NVFP4 26 days ago

NVFP4 vs FP8 on an RTX PRO 6000 Blackwell (vLLM 0.24): sadly, FP4 is still not faster than FP8 - Qwen3.6‑27B

👀👍 13

1

#8 opened 26 days ago by

janreges3

New activity in rico03/Qwen3.6-27B-Claude-Opus-Reasoning-Distilled 3 months ago

Chat-template fix: occasional </think> leak + body duplication on long-context tasks (patched template attached)

1

#3 opened 3 months ago by

janreges3

Thanks and request for FP8 version

3

#2 opened 3 months ago by

janreges3

New activity in Qwen/Qwen3.5-35B-A3B 5 months ago

vLLM - Looping prevention

👍 1

1

#39 opened 5 months ago by

janreges3

New activity in Qwen/Qwen3-Embedding-4B 9 months ago

How to set MRL (variable dimensions) in vLLM

❤️ 1

4

#21 opened 9 months ago by

janreges3

New activity in BCCard/Qwen3-235B-A22B-Thinking-2507-NVFP4A16 11 months ago

Request for NVFP4A16 model Qwen3-30B-A3B 2507 (Thinking & Instruct)

#1 opened 11 months ago by

janreges3

liked 3 models 12 months ago

Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8

Text Generation • 31B • Updated Dec 3, 2025 • 1.43M • 191

QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix

Text Generation • 20B • Updated Sep 5, 2025 • 12.4k • 10

BCCard/Qwen3-235B-A22B-Thinking-2507-NVFP4A16

133B • Updated Jul 28, 2025 • 5 • 2