2 x 5070ti Qwen 27B full config / stats
Summary
Technical post sharing performance stats for running Qwen 27B on 2x RTX 5070 Ti GPUs with vLLM cu129-nightly, achieving up to 94-87 tps decode and 170k GPU KV cache.
Similar Articles
2 old RTX 2080 Ti with 22GB vram each Qwen3.6 27B at 38 token/s with f16 kv cache
A user shares their setup using two modded RTX 2080 Ti GPUs with 22GB VRAM each to run Qwen 3.6 27B at 38 tokens/s with llama.cpp, including tips on power limiting, tensor split mode, and KV cache settings.
Best Settings for 48GB VRAM + Qwen 3.6 27B
A user shares optimized settings for running Qwen3.6 27B (Q8_0) on a dual GPU setup (RTX 4090 + RTX 3090) with llama.cpp, achieving 75-100 t/s and 1500 pp with 250k context.
@malikwas1f: 308 tok/s aggregate on 2× RTX 3090 — no NVLink Qwen3.8-27B on vLLM, 32 concurrent streams. Enough to feed a whole swarm…
A performance report and guide for running the Qwen3.8-27B model on dual RTX 3090 GPUs using vLLM, achieving 308 tokens per second with 32 concurrent streams, with a GitHub repository for local deployment configurations.
Ternary Qwen3.6 27B Tested on 3090!
User tests ternary quantized Qwen3.6 27B on an RTX 3090, achieving 60 tk/s with two slots and 100k KV cache using 21GB VRAM, with good quality and stable tool calls.
EXPERIMENT: Qwen3.8-2.4T-A95B running locally on an RTX 5090 + RTX 5060 Ti at ~0.80 tok/s
An experiment running the Qwen3.8-2.4T-A95B MoE model locally on dual consumer GPUs (RTX 5090 + 5060 Ti) with llama.cpp, achieving ~0.8 tok/s with MTP speculative decoding enabled.