Gavin Whittaker

gavwhittaker

6 20

AI & ML interests

None yet

Recent Activity

reacted to bytkim's post with 🔥 3 days ago

Qwen3.6-27B-pi-tune v2 is coming plus its sibling 35B-A3B variant I just wanted to share an update on the progress of future releases for Qwen3.6-pi-tuned family models. Both 27B and 35B models are now unified under native think/no-think functionality. The biggest lesson I started to learn after reviewing many suggestions: Fine-tuning for local open-weight agents isn't just about raw coding capability or benchmark numbers. Harness fluency, tool-calling, validation loops, and user-facing behavior matter just as much, sometimes more. That insight and philosophy is exactly what v2 is based on. Although it hasn't even been a month since the original release I wanted to get out the 35B-A3B variant as soon as possible due to popular demand. With the current and upcoming releases of a new class of Agentic LLM's (Fable, GPT5.6, etc) expect v3 to be the best yet. For everyone already running the original: what's it doing well, and what makes you reach for a different model? These suggestions help shape future releases. https://huggingface.co/collections/bytkim/qwen36-pi-tune PS: Heres a sneak peek at the newest version with the new 35B-A3B variant performing a one shot task. 😁

upvoted a collection 3 days ago

Qwen3.6 Pi-Tune

liked a model 9 days ago

bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF

View all activity

Organizations

None yet

liked a model 9 days ago

bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF

Image-Text-to-Text • 27B • Updated Jun 20 • 2.19k • 59

liked a model 25 days ago

Brian6145/Qwen3.6-27B-Claude-Opus-DeepSeek-Distilled-Imatrix-MTP-GGUF

Text Generation • 27B • Updated 26 days ago • 40.7k • 18

liked a model about 2 months ago

mradermacher/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF

Translation • 31B • Updated May 18 • 722 • 2

liked a model 2 months ago

llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF

Image-Text-to-Text • 31B • Updated May 23 • 15.9k • 35

liked 3 models 3 months ago

liked 2 models 4 months ago

Jackrong/Qwopus3.5-27B-v3.5-GGUF

Image-Text-to-Text • 27B • Updated Jul 9 • 882 • 46

Jackrong/Qwopus3.5-27B-v3-GGUF

Image-Text-to-Text • 27B • Updated Jul 9 • 1.3k • 351

liked a model 5 months ago

unsloth/gemma-3-12b-it-GGUF

Image-Text-to-Text • 12B • Updated Aug 14, 2025 • 65.9k • 193

liked 8 models about 1 year ago

unsloth/gpt-oss-20b-GGUF

Text Generation • 21B • Updated Dec 19, 2025 • 522k • 768

mradermacher/Qwen-Coder-DeepSeek-R1-14B-GGUF

15B • Updated Mar 8, 2025 • 185 • 4

unsloth/Qwen2.5-Coder-32B-Instruct-128K-GGUF

33B • Updated Nov 15, 2024 • 5.45k • 80

unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

Text Generation • 8B • Updated Jun 16, 2025 • 46.2k • 439

unsloth/DeepSeek-R1-0528-GGUF

Text Generation • 671B • Updated Jun 15, 2025 • 6.45k • 202

deepseek-ai/DeepSeek-Coder-V2-Instruct

Text Generation • 236B • Updated Aug 21, 2024 • 7.34k • 698

Qwen/Qwen3-235B-A22B

Text Generation • 235B • Updated Jul 26, 2025 • 549k • • 1.11k

Skywork/Skywork-OR1-32B

33B • Updated May 29, 2025 • 25 • 22

liked 2 Spaces over 1 year ago

Qwen3 Demo

📊

857

Chat with an AI assistant that thinks before answering

C4AI Command Models

🌟

1.52k

Generate answers to your questions