cd/entity/Qwen 3.6 35B MoE· home› entities› Qwen 3.6 35B MoE
grep -l @qwen 3.6 35b moe /news/*.json | wc -l → 1

Qwen 3.6 35B MoE

mentions 1 type Person feed RSS

// recent coverage 1 mentions

22:33
2026-07-24
gilesthomas.com
large-language-models

Benchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090

Benchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090 using Unsloth's UD-IQ4_NL_XL quantisation achieved up to 140 tokens per second for generation and over 3,300 tok/s for prompt processing with a…

// co-occurs with top 6 entities
RTX 3090 1 Llama.cpp 1 Unsloth 1 Hugging Face 1 Intel Arc B70 Pro 1 RTX 5090 1
// topics top 3 topics
large language models 1 ai infrastructure 1 ai tools 1