SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF
Image-Text-to-Text • 177B • Updated • 4.22M • 813
Mert Özkan
47Hunter47
AI & ML interests
None yet
Recent Activity
liked a model 6 days ago
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF updated a collection 6 days ago
Local llm liked a model 6 days ago
speridlabs/idolOrganizations
None yet
liked a
model 6 days ago
updated a
collection 6 days ago
liked a
model 6 days ago
New activity in DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF about 1 month ago
RTX 5090 32GB VRAM 128GB VRAM test results
❤️ 6
8
#4 opened about 2 months ago
by 
differentiator
IQ3_XXS 23tps on ASUS Z13 64GB RAM (AMD Ryzen™ AI MAX+ 395)
3
#21 opened about 2 months ago
by 
xlazom00
Speed tests on a 3060 laptop with 48GB RAM
2
#31 opened about 1 month ago
by 
2vibeornot2vibe
Benchmark & Reproduction Setup: Qwen3.8-Flash-Next GSQ-RCO IQ3_XXS (24.82 t/s at full 262k context on single RTX 3090)
8
#33 opened about 1 month ago
by 
AMonrroy
New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU about 1 month ago
There has always been a problem with prematurely stopping the output.
6
#24 opened about 1 month ago
by 
win10
reacted to GoktugD's post with 👍 about 2 months ago
Post
3,165
🇹🇷 **A 1B Turkish OCR model vs. Baidu OCR.**
We ran both models on the **same Turkish enterprise documents**.
The result:
**Werea-DocOCR-1B → 99.9**
**Baidu Unlimited-OCR → 47.9**
Same documents.
Same evaluation.
And Werea-DocOCR is only **1B parameters**.
It was built specifically for difficult Turkish enterprise documents:
📄 invoices
📑 contracts
🏦 bank receipts
💼 payroll
🚗 vehicle documents
📋 SGK-style tables
📱 scanned & phone-captured documents
But benchmarks aren't enough.
**Give me a Turkish document that you think will break it.**
We'll test the hardest ones and publish the failures.
🤗 Model:
Werea-co/Werea-DocOCR-1B
📚 Dataset:
Werea-co/werea-tr-doc-ocr-enterprise-v2
🇹🇷 Built in Türkiye. Open on Hugging Face.
#OCR #DocumentAI #HuggingFace #TurkishAI
We ran both models on the **same Turkish enterprise documents**.
The result:
**Werea-DocOCR-1B → 99.9**
**Baidu Unlimited-OCR → 47.9**
Same documents.
Same evaluation.
And Werea-DocOCR is only **1B parameters**.
It was built specifically for difficult Turkish enterprise documents:
📄 invoices
📑 contracts
🏦 bank receipts
💼 payroll
🚗 vehicle documents
📋 SGK-style tables
📱 scanned & phone-captured documents
But benchmarks aren't enough.
**Give me a Turkish document that you think will break it.**
We'll test the hardest ones and publish the failures.
🤗 Model:
Werea-co/Werea-DocOCR-1B
📚 Dataset:
Werea-co/werea-tr-doc-ocr-enterprise-v2
🇹🇷 Built in Türkiye. Open on Hugging Face.
#OCR #DocumentAI #HuggingFace #TurkishAI
liked a
model about 2 months ago
commented on DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS) about 2 months ago
I have been using the new qwen3.8-27 fine-tunes of DavidAu. To be honest, i didn't notice any improvement in intelligence. Only less thinking tokens. that is it.
upvoted an article about 2 months ago
Article
DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)
DedeProGames
• • 22 New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF about 2 months ago
liked a
model about 2 months ago
New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF about 2 months ago
Tool / Agent / Agentic -> Corrected Jinja template for tools / agents / agentic work.
🚀🔥 3
31
#10 opened about 2 months ago
by 
DavidAU
Is this model same as Q4KM for coding related tasks?
8
#22 opened 2 months ago
by 
soyalemujica
liked a
model about 2 months ago
