Ebenge Usip

eusip's activity

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

liked 2 models 3 days ago

chatnerdie/Qwen3.8-Flash-Next-EXL3-Sushi

Image-Text-to-Text • 37B • Updated 20 days ago • 130 • 4

beamster/Qwen3.8-Flash-Next-Sushi-4bpw

Image-Text-to-Text • 37B • Updated 4 days ago • 1.57k • 21

reacted to beamster's post with ❤️ 3 days ago

view post

Post

6,841

Last Qwen3.8 Flash update with STQ 2.75bpw v2.0 pack. It moves away from hybrid affine/stq format to pure STQ with +15% quality to match oQ4e. 64GB users can enjoy this while waiting for Qwen 4!

Require Sushi 1.5.1 ro run.

See translation

❤️

6

6

👍

1

1

🔥

1

1

+

Reply

updated a collection 13 days ago

Jackrong MLX Conversions

Collection

MLX oQ conversions of Jackrong models. Each entry notes the quantization level, dtype variant, and whether vision/MTP are preserved. • 2 items • Updated 13 days ago

published 2 models 14 days ago

sermonis-ai/Kestrel-4B-Coder-oQ4e-fp16-mtp

Image-Text-to-Text • 5B • Updated 14 days ago • 256 • 1

sermonis-ai/Kestrel-4B-Coder-oQ4e-mtp

Image-Text-to-Text • 5B • Updated 14 days ago • 168 • 2

updated 2 models 14 days ago

sermonis-ai/Kestrel-4B-Coder-oQ4e-fp16-mtp

Image-Text-to-Text • 5B • Updated 14 days ago • 256 • 1

sermonis-ai/Kestrel-4B-Coder-oQ4e-mtp

Image-Text-to-Text • 5B • Updated 14 days ago • 168 • 2

liked 2 models 3 months ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 3 days ago • 7.51M • • 19.5k

cafepm/GLM-4.7-Flash-REAP-23B-A3B-Q3Q4-GGUF

Text Generation • 23B • Updated Sep 5 • 42 • 1

New activity in Jackrong/Qwopus3.6-27B-Coder 4 months ago

Have you considered RYS?

🔥 1

1

#4 opened 5 months ago by

Diablo-D3

liked a dataset 5 months ago

Avtrkrb/combined-reasoning-opus-4.6-opus-4.7-kimi-k2.5-kimi-k2.6-glm-5.1

Viewer • Updated Jun 5 • 1.33M • 141 • 13

liked 2 models 5 months ago

Jackrong/Qwopus3.6-27B-v2-MTP-GGUF

Image-Text-to-Text • 0.5B • Updated Jul 9 • 6.64k • 394

Jackrong/Qwopus3.5-4B-v3-MTP-GGUF

4B • Updated May 22 • 1.06k • 20

upvoted 3 collections 5 months ago

🚀 Qwen-MTP

Collection

⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy. • 9 items • Updated Jun 29 • 37

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled-v2

Collection

8 items • Updated Jul 1 • 104

💻 Qwopus-Coder

Collection

Reasoning-distilled coding models optimized for specialized domains like agentic workflows. • 14 items • Updated 5 days ago • 61

liked 2 models 7 months ago

tvall43/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-gguf

Text Generation • 14B • Updated Mar 9 • 2.97k • 48

Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-6bit

Text Generation • 9B • Updated Mar 7 • 414 • 8