Can I Run Yi 1.5 Family on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
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 Q6_K needs about 31 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~1 GB before the runtime starts swapping. Expect ~41.7 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~41.7 tok/s
Get a personalized upgrade path →
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 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 32 GB |
| Memory bandwidth | 1792 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
Yi 1.5 Family on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 32 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 | ✓ Yes | 8K | ~41.7 tok/s | 28.2 GB |
| Q5_K_M | 27.2 GB | ✓ Yes | 16K | ~47.3 tok/s | 24.4 GB |
| Q4_K_M | 23.6 GB | ✓ Yes | 16K | ~54.2 tok/s | 20.8 GB |
| Q3_K_M | 17.5 GB | ✓ Yes | 16K | ~71.9 tok/s | 14.7 GB |
| Q2_K | 14.1 GB | ✓ Yes | 16K | ~87.6 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 | ~54.2 tok/s |
| Yi 1.5 9B Chat | 6.9 GB | ✓ Fits | ~153.6 tok/s |
What to watch out for
- Only ~1 GB of headroom at Q6_K: a longer context or a second application can push this into swapping.
RTX 5090 desktop limitations
- 575 W board power — budget for a 1000 W+ PSU and the heat it puts into the room.
- Models larger than 32 GB must offload to system RAM, which costs roughly an order of magnitude in speed.
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.
- 32 GB of VRAM on the NVIDIA GeForce RTX 5090 at 1792 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
Can I run Yi 1.5 Family on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Yes, but it is tight — Yi 1.5 34B Chat at Q6_K needs about 31 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~1 GB before the runtime starts swapping. Expect ~41.7 tok/s (estimated), with room for about 8,192 tokens of context.
Which quantization of Yi 1.5 Family should I use on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Q6_K — it needs about 31 GB of the 32 GB available, downloads as roughly 28.2 GB, and runs at an estimated 41.7 tokens/sec with up to 8K of context.
What limits Yi 1.5 Family on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Computers
Other Models on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)
- Aya Expanse on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)
- BitNet b1.58 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)
- Bonsai 27B on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)
- Codestral on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)
- Cogito v1 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)
Yi 1.5 Family on GPUs
- Yi 1.5 Family on NVIDIA GeForce RTX 5090
- Yi 1.5 Family on NVIDIA GeForce RTX 5070
- Yi 1.5 Family on NVIDIA GeForce RTX 5060 Ti 8GB
- Yi 1.5 Family on NVIDIA GeForce RTX 5060
What This Model Is Good At
Model & Tools
← Can I Run It? | Yi 1.5 Family model page | Check your hardware