Paper page - Qwen-Image-Flash: Beyond Objective Design
["qwen3"]
Search
All sources
huggingface.co
49
xda-developers.com
29
blogs.nvidia.com
11
developer.nvidia.com
10
amd.com
8
wccftech.com
6
aws.amazon.com
4
cnx-software.com
3
theregister.com
1
macrumors.com
1
9to5mac.com
1
neowin.net
1
Tracked topic
Qwen3
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
Videos
More videosI switched my local AI setup to AMD's Lemonade after Nvidia support landed, and solved my local AI portability problem
…Model Backend TTFT (ms) TPS VRAM peak (GB) Llama 3.2 3B Vulkan 188 78.3 4.0 Qwen3 8B (Q4_1) ROCm 95 41.2 6.6 Qwen3 8B (Q4_1…
I wrote a script to run Claude Code with my local LLM, and skipping the cloud has never been easier
…The way it handles tool integration, file edits, and permissions just feels more polished to me, and I've had better success with local models like Qwen3 Coder Next with Claude Code…
AMD's GAIA Defaults To Better Model, Continued Improvements For Local AI
["amd","qwen3","google-gemma"]
Discussions and forums
Qwen3.5 35B A3B uncensored heretic Native MTP Preserved is Out Now With the Full 785 MTPs Preserved and Retained, Available in Safetensors, GGUFs. NVFP4, NVFP4 GGUFs and GPTQ-Int4 Formats
Safetensors, llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved: https://huggingface.co/llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved GGUFs, llmfan46/Qwen3.5-35B-A3B-uncensored-here…
Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090
Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090
5
2
We got 207 tok/s with Qwen3.5-27B on an RTX 3090
We got 207 tok/s with Qwen3.5-27B on an RTX 3090
165
52
Qwen3.7 Max scored by Artificial Analysis, 27B/35B waiting room
https://preview.redd.it/42ak5qmus82h1.png?width=1133&format=png&auto=webp&s=744ea3dfc06c83d0c4d8aa128c39b3238b17d7be Qwen 3.7 Max sitting at 5th, pretty much on par with GPT 5.4 (xhigh) and a notch above the just release…
Show HN: Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant
https://w418ufqpha7gzj-80.proxy.runpod.netStarted for myself, but since Im not using it continuously, sharing it:Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant (TheTom/llama-cpp-turboquant) on RTX 3090 (Runpod spo…
4
2
Paper page - WriteSAE: Sparse Autoencoders for Recurrent State
…Atom substitution beats matched-norm ablation on 92.4% of n=4{,}851 firings at Qwen3.5-0.8B L9 H4, the 87-atom population test holds at 89.8%, the closed…
I gave a local LLM full control over my Proxmox node, and it worked better than I expected
…Since my RTX 3080 Ti can drive the bulky Qwen3.6-35B-A3B with relative ease thanks to MoE offloading, I ran it with llama-server and paired it with the Pi…
NVIDIA Shows DLSS 4, Path Tracing, and RTX Mega Geometry with New Downloadable Bonsai Diorama Demo
…In other NVIDIA news, ACE (Avatar Cloud Engine) can now use the open-source Qwen3-8B AI model as an In-Game Inferencing (IGI) SDK plug-in. This simplifies integration within a…
AMD Ryzen™ AI Halo for AI Developers
["amd","ryzen","qwen3","windows-11"]
I replaced my ChatGPT subscription with a local AI coding tool and haven't looked back
…Related I finally found a local LLM I actually want to use for coding Qwen3-Coder-Next is a great model, and it's even better with Claude Code as a harness…
I stopped running the biggest local LLM that could fit, and a 2B model handles 90% of what I need
…Related Qwen3.5-9B tops every AI benchmark right now, but that's not how you should pick a model There's a lot more to a model than just benchmarks. How…