Qwen 3.6 35B MoE benchmarked locally on an RTX 3090 with 3B active params
gpjt · hn · 2026-07-25
A blog post benchmarks Qwen 3.6 35B MoE with 3B active parameters on an RTX 3090.
The focus is on how well a large MoE model can run locally on consumer hardware, making this more of a deployment and inference-cost piece than a pure model announcement. It is useful for people evaluating local setups and quantized performance.
More from Infra
- A100 rental prices still rising in 2026 per a16z data, Jevons paradox hits compute — VraserX · 2026-10-27
- Anthropic S-1 reveals $800B+ in off-books future compute commitments — GaryMarcus · 2026-10-27
- ~42% of Anthropic's ~11GW contracted compute is NVIDIA GPUs — ns123abc · 2026-10-27
- EdgeRock-4B holds KV cache at 72 MiB across 256K context, 99.1% smaller than Qwen3.5-4B — alifcoder · 2026-10-27
- RTX 5080 price jumps from $1658 to $2318 in ten days on Amazon — Frizzy-MacDrizzle · 2026-10-27
- ComfyUI on 12GB VRAM: measured peaks show offloading turns 24s into 11 minutes — Impossible-Mail-4619 · 2026-10-27