NVIDIA graphics card · used · data 2026-10-15

GeForce RTX 3090 (used) for local AI.

Name: GeForce RTX 3090 (used)
Brand: NVIDIA

With 24 GB it runs Qwen3.8 27B (needs 22.7 GB). 56 models fit. Published speed: gpt-oss-20b at 147.53 tokens/sec.

Memory24 GB

vram

Bandwidth936 GB/s

Higher means faster answers.

PriceFrom about $1,430

As of 2026-10-02. Check before buying.

Which models fit

By memory option.

Usable: 75% on Macs and shared-memory PCs, VRAM minus 1 GB on graphics cards (estimates).
Memory	Usable	Models that fit	Best three
24 GB	23 GB	56	Qwen3.8 27B (22.7 GB), Qwen3.5 27B (21.5 GB), Qwen3.6 27B (21.5 GB)

Speed

Published speeds.

Measured by others, with sources. Not our tests.

Model	Tokens/sec	Engine	Setup	Source
gpt-oss-20b	147.53	llama.cpp (Linux, flash attention) · MXFP4	—	community-measured · 2025-10-26

Questions

Short answers.

What is the best local LLM for the GeForce RTX 3090 (used)?: With 24 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 56 of 124 models fit.
How fast is the GeForce RTX 3090 (used) for local AI?: Published: gpt-oss-20b at 147.53 tokens/sec (llama.cpp (Linux, flash attention), ). These are other people's measurements, not ours.
How much does the GeForce RTX 3090 (used) cost?: From about $1,430 (as of 2026-10-02). 2026 prices are inflated by the memory-chip shortage; check before buying.

Specs from Wikipedia – List of Nvidia GPUs (spec tables) (2026-10-15). Prices are approximate and dated; 2026 prices are inflated by the memory-chip shortage.

AGENT VIEW · text/markdown · or send Accept: text/markdown

# GeForce RTX 3090 (used) for local AI

URL: https://insidethemachine.ai/machines/rtx-3090
Type: NVIDIA graphics card. Chip: RTX 3090 (used). Memory: vram, options 24 GB. Bandwidth: 936 GB/s. Spec source: https://en.wikipedia.org/wiki/List_of_Nvidia_graphics_processing_units (2026-10-15).
Price: from about $1,430 (2026-10-02, approximate). Status: used.

## Which models fit

| memory GB | usable GB | models that fit | best 3 |
|---|---|---|---|
| 24 | 23 | 56 | Qwen3.8 27B (22.7 GB), Qwen3.5 27B (21.5 GB), Qwen3.6 27B (21.5 GB) |

## Published speeds (not our tests)

- gpt-oss-20b: 147.53 tok/s decode, 4400.3 tok/s prompt (llama.cpp (Linux, flash attention), MXFP4, , community-measured) https://www.hardware-corner.net/guides/gpt-oss-20b-gpu-benchamrks/ (2025-10-26)

Notes: eBay median of 35 clean used sales (range $950–$1,799). The classic budget 24GB card; NVLink-capable.

## Questions

**What is the best local LLM for the GeForce RTX 3090 (used)?**
With 24 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 56 of 124 models fit.

**How fast is the GeForce RTX 3090 (used) for local AI?**
Published: gpt-oss-20b at 147.53 tokens/sec (llama.cpp (Linux, flash attention), ). These are other people's measurements, not ours.

**How much does the GeForce RTX 3090 (used) cost?**
From about $1,430 (as of 2026-10-02). 2026 prices are inflated by the memory-chip shortage; check before buying.