Maksim Galinovskii

galmsx's activity

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

liked 3 models about 1 month ago

TelperionAI/Qwen3.8-27B-NVFP4-AWQ-AutoRound

Image-Text-to-Text • 20B • Updated Sep 2 • 219 • 7

Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound

Image-Text-to-Text • 7B • Updated Aug 17 • 573 • 12

wasifb/ThinkingCap-Qwen3.8-27B-AutoRound-W4A16

Image-Text-to-Text • 3B • Updated Sep 25 • 1.57k • 6

liked 4 models about 2 months ago

bottlecapai/ThinkingCap-Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Oct 6 • 4.57k • 195

angrykirc/ThinkingCap-Qwen3.8-27B-INT8-W8A8-imatrix

Text Generation • 28B • Updated Sep 26 • 68 • 1

RukaRat/Qwen3.8-27B-INT8-W8A8-imatrix-heretic-MTP

Image-Text-to-Text • 27B • Updated Sep 19 • 240 • 2

RukaRat/Qwen3.8-27B-INT8-W8A8-imatrix-MTP

Image-Text-to-Text • 27B • Updated Sep 23 • 549 • 7

New activity in RukaRat/Qwen3.8-27B-INT8-W8A8-imatrix-MTP about 2 months ago

Perfect quant for sglang!

1

#3 opened about 2 months ago by

galmsx

liked 4 models 2 months ago

LiconStudio/LTX-2.5-Multiple-Subject-Reference

Updated Sep 23 • 14.5k • 107

protogeni/Qwen3.8-27B-Uncensored-W4A16-RTX3090-MTP4

Image-Text-to-Text • 28B • Updated 19 days ago • 279 • 7

alibaba-pai/MiniMax-H3-Acc-LoRAs

Text-to-Video • Updated Aug 27 • 57.3k • 279

JonathanColetti/Qwen3.8-27B-Uncensored-GGUF

Text Generation • 27B • Updated Aug 29 • 2.47M • 1.97k

liked 3 models 3 months ago

lued/Qwen3.8-27B-INT8-W8A16-DFlash2

Image-Text-to-Text • 27B • Updated Aug 21 • 1.14k • 35

TenStrip/10Eros-Max

Image-Text-to-Video • Updated 3 days ago • 982

lued/Qwen3.8-27B-INT8-W8A16-MTP

Image-Text-to-Text • 28B • Updated Aug 15 • 13.6k • 97

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 3 months ago

Multi-turn instability: FP8-quantized linear_attn recurrent projections cause agent "forgetting"

👀 1

4

#6 opened 4 months ago by

galmsx

liked a model 3 months ago

AlexanderKyng/KAT-Codex-V2.5-Dev-48Gb

Image-Text-to-Text • 35B • Updated Jul 30 • 262 • 4

New activity in josefprusa/ThinkingCap-Qwen3.6-27B-int4-AutoRound-v1 4 months ago

Excellent performance and quality on 2x3090 for coding tasks!

1

#2 opened 4 months ago by

galmsx

liked 2 models 4 months ago

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Text-to-Speech • 2B • Updated Jan 29 • 1.35M • • 2.22k

josefprusa/ThinkingCap-Qwen3.6-27B-int4-AutoRound-v1

Text Generation • 6B • Updated Jul 7 • 152 • 50