Michael W

michaelw9999's activity

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

New activity in Jackrong/Qwopus3.6-27B-v2-MTP-GGUF about 2 hours ago

Benchmark source availability?

#10 opened about 2 hours ago by

michaelw9999

New activity in michaelw9999/Qwen3.6-27B-NVFP4-MTP-GGUF about 16 hours ago

Benchmarks: RTX 5090 Desktop — Performance & Intelligence (llama.cpp b9415, 230K ctx)

🚀👍 2

2

#3 opened 3 days ago by

raulgdm

New activity in michaelw9999/Qwen3.6-27B-NVFP4-MTP-GGUF 1 day ago

MTP layer

16

#1 opened 6 days ago by

iandennismiller

About MTP

3

#4 opened 1 day ago by

Summeroff

New activity in michaelw9999/Qwen3.6-27B-NVFP4-MTP-GGUF 4 days ago

Performance on 5090 RTX Laptop (24gb VRAM)

5

#2 opened 6 days ago by

mgarf

New activity in michaelw9999/Qwen3.5-9B-NVFP4-MTP-GGUF 7 days ago

path to NVFP4-MTP-GGUF

➕ 1

2

#1 opened 10 days ago by

ghit72

Wrong number of tensors error

1

#2 opened 7 days ago by

praneeth222

New activity in Jackrong/Qwopus3.6-27B-v2-MTP-GGUF 7 days ago

Any plans to release an NVFP4 version?

1

#1 opened 10 days ago by

Rubrigate

New activity in michaelw9999/Qwen3.5-4B-MXFP6-GGUF 27 days ago

Updated the model with a new layout

#2 opened 27 days ago by

michaelw9999

New activity in michaelw9999/Qwen3.5-4B-MXFP6-GGUF 28 days ago

quantisation procedure request

1

#1 opened 28 days ago by

hugypufy

New activity in michaelw9999/Nemotron-Cascade-2-30B-A3B-NVFP4-GGUF 2 months ago

NVFP4 Quantizer

2

#1 opened 2 months ago by

pirola

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 2 months ago

187 tok/s on RTX 3090, 625K Context, Agent Coding (IQ4_XS + Hermes Agent)

🚀🔥 3

7

#20 opened 2 months ago by

ychenNLP

Official quantizations?

👍 2

6

#9 opened 2 months ago by

wijjjj