Can I Run Yi 1.5 Family on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Newer alternative. 01.AI has not released a newer model in this library. If you are choosing today, Qwen 3 is a comparable current option. View Qwen 3 →

Written by Jakub Rusinowski · Last updated May 13, 2024

Yes, but it is tight

Yes, but it is tight — Yi 1.5 34B Chat at Q4_K_M needs about 23.6 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~0.4 GB before the runtime starts swapping. Expect ~30.1 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: medium · Recommended quantization: Q4_K_M · Estimated speed: ~30.1 tok/s

Get a personalized upgrade path →

Buy this hardware AMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board power Deploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

RTX 3090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models	24 GB
Memory bandwidth	936 GB/s
Form factor	Desktop
Operating system	Windows or Linux
Memory upgradeable	Yes

Yi 1.5 Family on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization

Quant	Memory needed	Fits 24 GB?	Max context	Est. speed	Download
F16	71.6 GB	✗ No	—	—	68.8 GB
Q8_0	39.4 GB	✗ No	—	—	36.6 GB
Q6_K	31 GB	✗ No	—	—	28.2 GB
Q5_K_M	27.2 GB	✗ No	—	—	24.4 GB
Q4_K_M	23.6 GB	✓ Yes	8K	~30.1 tok/s	20.8 GB
Q3_K_M	17.5 GB	✓ Yes	16K	~40.7 tok/s	14.7 GB
Q2_K	14.1 GB	✓ Yes	16K	~50.5 tok/s	11.3 GB

Which Yi 1.5 Family sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Yi 1.5 34B Chat	23.6 GB	✓ Fits	~30.1 tok/s
Yi 1.5 9B Chat	6.9 GB	✓ Fits	~96 tok/s

What to watch out for

Only ~0.4 GB of headroom at Q4_K_M: a longer context or a second application can push this into swapping.

RTX 3090 desktop limitations

The cheapest route to 24 GB of VRAM, and the standard used-market recommendation for local LLMs.
Older architecture: no FP8 acceleration, and higher idle power than a current card.

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
24 GB of VRAM on the NVIDIA GeForce RTX 3090 at 936 GB/s.
64 GB of system RAM available for CPU offload when a model exceeds VRAM.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is computed from this model's published attention configuration.

FAQ