Mark Galyan

apollo-mg's activity

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

New activity in NousResearch/Arete-27B 2 days ago

A side effect worth knowing: Arete-27B vs base Qwen3.8-27B on questions about things that don't exist

👍👀 9

17

#23 opened 5 days ago by

apollo-mg

New activity in ricursiveAI/Ripple-65B-Preview 5 days ago

Invented-entity questions: Ripple-65B-Preview reasons until the budget runs out (M1 results)

1

#13 opened 5 days ago by

apollo-mg

New activity in CohereLabs/10-2026-qwen-investigation-traces 11 days ago

Follow Up Testing and Results

3

#6 opened 13 days ago by

apollo-mg

New activity in reflection/Beam-1.0-501B-A23B 25 days ago

Independent results: Beam at 2-bit on an abstention benchmark + reasoning_effort sweep

👀 4

#15 opened 25 days ago by

apollo-mg

New activity in reflection/Beam-1.0-501B-A23B 26 days ago

Thank you !!

❤️ 2

3

#13 opened 27 days ago by

pawarshardul

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF about 1 month ago

Knowledge and calibration check vs the unpruned GSQ-RCO IQ3_XXS

🔥 3

#19 opened about 1 month ago by

apollo-mg

New activity in ukisai/Swift1.5-Qwen3.8-Flash-Next about 2 months ago

First Look Results

#3 opened about 2 months ago by

apollo-mg

New activity in DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF about 2 months ago

Chat Template First Test

👍❤️ 2

3

#11 opened about 2 months ago by

apollo-mg

New activity in HemmingwayAI/Hemmingway-1 about 2 months ago

Overall, a good model.

15

#1 opened about 2 months ago by

RomanHammer

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF about 2 months ago

Reasoning Modes Work Well - Distinctly Different Thoughts Per Setting

🧠❤️ 3

7

#11 opened 2 months 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)

🔥👍 11

7

#18 opened about 2 months ago by

Jakaryun

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 2 months ago

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

❤️👍 9

4

#14 opened 2 months ago by

DavidAU

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored 2 months ago

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

🔥❤️ 2

8

#10 opened 2 months ago by

DavidAU

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 2 months ago

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

😎🔥 3

31

#10 opened 2 months ago by

DavidAU

liked a model 2 months ago

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

Image-Text-to-Text • 27B • Updated Sep 12 • 8.78k • 65

New activity in bartowski/ukisai_Swift-Qwen3.8-27b-GGUF 2 months ago

Thanks!

❤️ 3

#1 opened 2 months ago by

apollo-mg

New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 2 months ago

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

🔥👍 6

19

#4 opened 2 months ago by

DavidAU

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 2 months ago by

47Hunter47

New activity in bartowski/Qwen3.8-27B-GGUF 3 months ago

MTP layer quantization on Q8_0

2

#4 opened 3 months ago by

mbednarek360

New activity in Qwen/Qwen3.8-27B 3 months ago

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

🚀 6

5

#65 opened 3 months ago by

d4nnyy