Gittensor Model Hub

community

gittensor-model-hub

AI & ML interests

Fast, distilled, Blackwell-native AI built for RTX 5090/Pro 6000 and real-time agent workflows.

Recent Activity

jared89 published a model 7 days ago

gittensor-model-hub/SparkHermes-27B-v1-NVFP4

jared89 updated a model 7 days ago

gittensor-model-hub/SparkHermes-27B-v1-NVFP4

jared89 published a model 16 days ago

gittensor-model-hub/Swift-Qwen3.8-27B-NVFP4-RTX5090

View all activity

published a model 7 days ago

gittensor-model-hub/SparkHermes-27B-v1-NVFP4

Image-Text-to-Text • 15B • Updated 7 days ago • 103

updated a model 7 days ago

gittensor-model-hub/SparkHermes-27B-v1-NVFP4

Image-Text-to-Text • 15B • Updated 7 days ago • 103

published a model 16 days ago

gittensor-model-hub/Swift-Qwen3.8-27B-NVFP4-RTX5090

Image-Text-to-Text • 15B • Updated 16 days ago • 184

updated a model 16 days ago

gittensor-model-hub/Swift-Qwen3.8-27B-NVFP4-RTX5090

Image-Text-to-Text • 15B • Updated 16 days ago • 184

updated 3 models about 1 month ago

gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090

Image-Text-to-Text • 15B • Updated Sep 10 • 392k • 173

gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090-LMHead4

Image-Text-to-Text • 15B • Updated Sep 1 • 5.76k • 7

gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090-No-MTP

Image-Text-to-Text • 15B • Updated Sep 1 • 176

in gittensor-model-hub/Qwen3.8-27B-DSpark-NVFP4 about 2 months ago

Crashing with AssertionError: Can not alloc mamba cache

#1 opened about 2 months ago by

published a model about 2 months ago

gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090-LMHead4

Image-Text-to-Text • 15B • Updated Sep 1 • 5.76k • 7

updated a collection about 2 months ago

Qwen3.8-27B on RTX 5090

One 32 GB GPU: the NVFP4 checkpoint, its matched DSpark speculative drafter, and variants. • 4 items • Updated Aug 19 • 1

updated a Space about 2 months ago

README

published a model about 2 months ago

gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090-No-MTP

Image-Text-to-Text • 15B • Updated Sep 1 • 176

updated a model about 2 months ago

gittensor-model-hub/Qwen3.8-27B-DSpark-NVFP4

0.9B • Updated Aug 19 • 26.2k • 22

in gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090 about 2 months ago

Update chat_template.jinja

#7 opened about 2 months ago by

reality-interface

Update chat template

#5 opened about 2 months ago by

reality-interface

MTP compatability

#4 opened about 2 months ago by

Update chat template

#5 opened about 2 months ago by

reality-interface