AI Briefing#qwen
The latest AI and developer news about #qwen, with the original source and a short summary.
The latest AI and developer news about #qwen, with the original source and a short summary.
In a single H100 GPU benchmark, Gemma 4 E2B-it delivered the best results in both throughput and TTFT.
Tested KV cache quantization for Qwen3.6-27B on a 3090 eGPU with a 200k context.
On a 3070 8GB setup, Qwen3.6-35B ran faster with larger quants.
Moving the monitor to the iGPU raised llama.cpp token speed from 50t/s to 55t/s.
Gemma was sensitive to KV cache quantization, while Qwen held up relatively well.
A parser error in vLLM was found to cause malfunctioning Tool Calling functionality in Qwen models.
Qwen3.6 35B-A3B showed a prompt processing speed of 282 tokens per second on a Radeon 780M iGPU.
On a combination of m720q i7, 64GB RAM, and T1000 8GB, Qwen 3.6 27B recorded 20 TPS.
This week's Simon Willison newsletter was a large issue featuring a new chapter of Agentic Engineering Patterns and several links.
Qwen3.6 27B IQ4_XS recorded 22 tok/s on an RTX 5060 Ti 16GB.
OpenRouter's Qwen3.6 Plus input, output, and cache prices have been cut.
With llama.cpp ngram-mod speculative decoding, Qwen-3.6-27B speed rose to 136.75 t/s.
In a 2 x RTX Pro 6000 environment, Qwen3.6-27B delivered the best performance, while Qwen3.6-35B-A3B showed higher tps.
Qwen3.6-35B-A3B ran with 64K context on an RTX 5070 12GB.
Built a chat UI for Gemma-4-E4B using a Qwen-series model in about 8 minutes.
Recommended sampling parameters for each mode of Qwen3.6-27B have been released.
The 27B dense multimodal Qwen has unveiled coding performance on par with much larger models.
Connecting Qwen3.6 to Claude Code on a dual 3090 setup cut the estimated 8-hour cost from $142 to under $4.
Gemma4 and Qwen 3.5/3.6 were compared on RTX 5090 using the same document-writing task.
A 4-bit GPTQ-Pro quantized model has been released to run Qwen3.6-27B on Ampere GPUs.
On an RTX6000 Blackwell, Qwen 3.6 27B BF16 generated a Pac-Man HTML.
Qwen3.6-27B is a 27B dense model that claims coding performance surpassing the previous ultra-large MoE flagship.
A merged model combining Qwen3.6-35B-A3B with Qwopus and Holo3, along with benchmarks, has been released.