Qwen3.6-35B is now open source. Apache 2.0.
35B total params, only 3B active. Sparse MoE architecture punching way above its weight class.
* Agentic coding on par with models 10x its active size
* Strong multimodal perception and reasoning
* Thinking and non-thinking modes built in
The efficiency gap between open and closed source keeps closing.
35B total params, only 3B active. Sparse MoE architecture punching way above its weight class.
* Agentic coding on par with models 10x its active size
* Strong multimodal perception and reasoning
* Thinking and non-thinking modes built in
The efficiency gap between open and closed source keeps closing.
👾45❤2
HERE’S A LIST OF ALL THE AI MODELS DROPPED SO FAR THIS YEAR:
- Claude Opus 4.6
- Claude Sonnet 4.6
- Claude Opus 4.7
- Claude Mythos Preview
- Gemini 3.1 Pro
- Gemini 3 Flash
- Gemma 4 26B-A4B
- Gemma 4 variants
- GPT-5.3 Codex
- GPT-5.3 Codex Spark
- GPT-5.4
- GPT-5.4 mini
- GPT-5.4 nano
- Grok 4.20
- Grok 4
- Qwen 3.5
- Qwen3-Coder-Next
- Kimi K2
- Kimi K2.5
- DeepSeek V3.2
- GLM-5
- GLM-5.1
- Muse Spark
- Llama 4 Maverick
- MiniMax M2.5
- MiniMax M2.7
- MAI-Transcribe-1
- MAI-Voice-1
- MAI-Image-2
It’s one quarter into the year…
- Claude Opus 4.6
- Claude Sonnet 4.6
- Claude Opus 4.7
- Claude Mythos Preview
- Gemini 3.1 Pro
- Gemini 3 Flash
- Gemma 4 26B-A4B
- Gemma 4 variants
- GPT-5.3 Codex
- GPT-5.3 Codex Spark
- GPT-5.4
- GPT-5.4 mini
- GPT-5.4 nano
- Grok 4.20
- Grok 4
- Qwen 3.5
- Qwen3-Coder-Next
- Kimi K2
- Kimi K2.5
- DeepSeek V3.2
- GLM-5
- GLM-5.1
- Muse Spark
- Llama 4 Maverick
- MiniMax M2.5
- MiniMax M2.7
- MAI-Transcribe-1
- MAI-Voice-1
- MAI-Image-2
It’s one quarter into the year…
👾46
AliBaba
Qwen3.6-35B is now open source. Apache 2.0. 35B total params, only 3B active. Sparse MoE architecture punching way above its weight class. * Agentic coding on par with models 10x its active size * Strong multimodal perception and reasoning * Thinking and…
Qwen 3.6 35B makes Gemma 4 look like a joke.
These results are insane for a 35B parameter model.
These results are insane for a 35B parameter model.
Requirements to run:
- Minimum - 18GB ram
- Mac with 32GB+ unified memory.
- Decent speed: 24GB+ VRAM GPU (like RTX 4090)
👾48
JUST IN: OpenAI unveils GPT-Rosalind, an AI model aimed at accelerating drug discovery.
👾46
Media is too big
VIEW IN TELEGRAM
Anthropic released Claude Design 👀
A new tool to generate UI prototypes, slides, and one-pagers. Claude Design will be gradually rolled out to all paid plans shortly.
A new tool to generate UI prototypes, slides, and one-pagers. Claude Design will be gradually rolled out to all paid plans shortly.
👾51
BREAKING: Anthropic is now trading at an implied valuation of $1 trillion+ on secondary market platforms, surpassing OpenAI.
👾47 3
JUST IN: Top Chinese AI firm DeepSeek to raise money for the first time, at $10 billion+ valuation.
👾44 5 3 1
It's called 10-80-10.
10% — you do the research and context up front
80% — AI does the heavy lifting
10% — you tweak and finalize
Most people skip straight to the 80.
Then wonder why the output is trash.
10% — you do the research and context up front
80% — AI does the heavy lifting
10% — you tweak and finalize
Most people skip straight to the 80.
Then wonder why the output is trash.
👾47 3❤1
Claude Design is generating insane UI, designs & animations from just text.
Design will never be the same 🤯
10 wild examples:
Design will never be the same 🤯
10 wild examples:
👾45
Grok 4.3 (beta) is now available to SuperGrok and X Premium+ users!
👾46❤1
Good news! NVIDIA limited-time perk:
Claim a free 1-year API Key!
Hermes Agent now supports integration with the NVIDIA NIM platform, with real-world testing confirming the optional MiniMax 2.7 model.
The obtained API Key is valid for up to 12 months and is currently available.
Claim it while it's free.
Portal: build.nvidia.com
Claim a free 1-year API Key!
Hermes Agent now supports integration with the NVIDIA NIM platform, with real-world testing confirming the optional MiniMax 2.7 model.
The obtained API Key is valid for up to 12 months and is currently available.
Claim it while it's free.
Portal: build.nvidia.com
👾50 1
Anti-AI groups are now trying to take down AI with "data poisoning", the act of purposely flooding training models with false information to make the AI hallucinate.
👾47😈1