Qwen News & Updates
Your central hub for AI news and updates on Qwen. We're tracking the latest articles, discussions, tools, and videos from the last 7 days.
All (17)
1 news
16 posts
0 tools
0 videos
26
May
25
May
24
May
23
May
22
May
21
May
20
May
No tools found
Check back soon for new AI tools
No videos found
Check back soon for video content
26
May
25
May
24
May
23
May
22
May
21
May
20
May
Community talk
AI content detector based on Qwen 0.8b fine-tuned on Pangram dataset
1000 tps generation on Qwen3.6 27B with V100s
hipEngine: Fast Native Qwen 3.6 Inference for RDNA3 (Strix Halo, 7900 XTX)
Qwen3.6-35B-A3B-Uncensored-Genesis-APEX-MTP
Did a 30 runs of llama-bench to find optimal settings for my use case (Frigate and HomeAssistant) on my MI60 32gb VRAM GPU - two models tested Gemma4 and Qwen3.6 - Figured I'd share in case it helps anyone else
Qwen3.6 27B Pure Quant: 40 tok/s on 16 GB VRAM
Qwen3.6-35B-A3B Q4 262k context on 8GB 3070 Ti = +30tps
BeeLlama v0.2.0 – major DFlash update. Single RTX 3090: Qwen 3.6 27B up to 164 tps (4.40x), Gemma 4 31B up to 177.8 tps (4.93x). Prompt processing speed near baseline.
ByteShape Qwen3.6-35B-A3B: 30% faster than Unsloth IQ on 6GB VRAM laptop
Qwen-27B-IQ4_KS for ik_llama.cpp, especially for NVIDIA with 16GB VRAM
110 tok/s with 12GB VRAM on Qwen3.6 35B A3B and ik_llama.cpp
RTX 5080 16GB: Qwen3.6 35B MoE at 128k context — 56 tok/s, and why MTP doesn't help
The pacman benchmark: finally a viable local agentic coding agent with Qwen 3.6 27b
Qwen is cooking hard
qwen3.6-35b-a3b-mtp running on GTX 1060 6GB
Qwen 3.7 Max scores 60.6% on SWE-Bench Pro