Mark Galyan

apollo-mg's activity

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

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF about 21 hours ago

Knowledge and calibration check vs the unpruned GSQ-RCO IQ3_XXS

#19 opened about 21 hours ago by

apollo-mg

New activity in ukisai/Swift1.5-Qwen3.8-Flash-Next 3 days ago

First Look Results

#3 opened 3 days ago by

apollo-mg

New activity in DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF 3 days ago

Chat Template First Test

👍❤️ 2

3

#11 opened 4 days ago by

apollo-mg

New activity in Altworld/Hemmingway-1 9 days ago

Overall, a good model.

15

#1 opened 12 days ago by

RomanHammer

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 17 days ago

Reasoning Modes Work Well - Distinctly Different Thoughts Per Setting

👍❤️ 3

7

#11 opened 21 days ago by

dilletante

We benched TWIN-TURBO-709-L 13 ways against TURBO-735 on a 320-tool agent harness: templates, reasoning modes, and why thinking OFF won (51 runs, one GPU)

🔥👍 10

5

#18 opened 18 days ago by

Jakaryun

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 19 days ago

!!!!!!!!!!!! => NEW GGUFS updated for tools/reasoning (FIXES);

👍❤️ 9

4

#14 opened 20 days ago by

DavidAU

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored 19 days ago

Tool / Agent / Agentic -> Corrected Jinja template for tools / agents / agentic work.

👀🔥 2

8

#10 opened 21 days ago by

DavidAU

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 20 days ago

Tool / Agent / Agentic -> Corrected Jinja template for tools / agents / agentic work.

🚀🔥 3

31

#10 opened 21 days ago by

DavidAU

liked a model 20 days ago

bartowski/ukisai_Swift-Qwen3.8-27b-GGUF

Image-Text-to-Text • 27B • Updated 21 days ago • 35.8k • 59

New activity in bartowski/ukisai_Swift-Qwen3.8-27b-GGUF 20 days ago

Thanks!

❤️ 3

#1 opened 20 days ago by

apollo-mg

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 20 days ago

Tips and Troubleshooting / Fixes // getting max performance // etc etc.

🔥👍 6

19

#4 opened 21 days ago by

DavidAU

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 21 days ago

FIXED Jinja // Agentic/tool-calling use: mid-tool-call stream drops + premature turn ends (base Qwen3.8 is fine in the same stack)

7

#7 opened 21 days ago by

47Hunter47

New activity in bartowski/Qwen3.8-27B-GGUF about 2 months ago

MTP layer quantization on Q8_0

2

#4 opened about 2 months ago by

mbednarek360

New activity in Qwen/Qwen3.8-27B about 2 months ago

we quantized Qwen3.8-27B and compared it with community GGUFs on 4x RTX 5090!

🚀 6

5

#65 opened about 2 months ago by

d4nnyy

liked a model about 2 months ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.93M • • 16.8k

New activity in Akicou/GLM-4.7-Flash-REAP-50-GGUF about 2 months ago

Pruning Method

1

#2 opened about 2 months ago by

apollo-mg

New activity in LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUF 2 months ago

HermesBench Results

🤯 5

11

#13 opened 2 months ago by

apollo-mg

liked a model 2 months ago

poolside/Laguna-S-2.1

Text Generation • 118B • Updated Aug 19 • 132k • • 1.04k

New activity in poolside/Laguna-S-2.1 2 months ago

THANK YOU!

❤️🚀 19

1

#3 opened 2 months ago by

apollo-mg