llamaperf

Qwen3.8 27B

on NVIDIA RTX 3090 · 197,000 ctx

Tone: positiveNVIDIA hardware
Oct 31, 2026
Throughput
30.0 t/s gen
Quant
Q4_K_M (GGUF)
VRAM reported
24 GB

Use cases

agentic

Summary

User reports Qwen3.8 27B at 30 t/s single-stream on an RTX 3090 24GB, with aggregate throughput rising to 110 t/s across 12 concurrent agents. Setup is Q4_K_M with 197k context; the engine is not named. Per-agent speed falls from 30 t/s at one agent to 9 t/s at 12 and 7 t/s at 16, while total throughput plateaus near 110 t/s. The user calls 12 agents the optimum per machine and notes each agent gets less context as concurrency rises.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Qwen3.8 27B at 4-bit by hardware

Bars are medians on one scale, 0 to 94.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Models most run on the NVIDIA RTX 3090

Bars are medians on one scale, 0 to 111.7 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Everything reported on the NVIDIA RTX 3090 →Every Qwen3.8 report →Estimate Qwen3.8 on this card →