Can the NVIDIA RTX 4090 run Llama 3.1 70B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
No. Even at Q4_K_M, Llama 3.1 70B needs about 46.1 GB, but the NVIDIA RTX 4090 has 24 GB usable. You could offload some layers to system RAM, but it will be very slow.
Run it on a rented GPU
On a cloud GPU with enough memory, the same command you'd use locally works:
ollama run llama3.1:70bAt Q4_K_M it needs about 46.1 GB, so pick a GPU with at least 48 GB.
New to this? Step-by-step setup for the RTX 4090
Run it in the cloud
Too big for the NVIDIA RTX 4090? Run Llama 3.1 70B on a rented GPU instead.
Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 24 GB the NVIDIA RTX 4090 can use.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 144.5 GB | Too big | — | |
| Q8_0 | Near-lossless | 78.3 GB | Too big | — | |
| Q6_K | Excellent | 61.2 GB | Too big | — | |
| Q5_K_M | Very good | 53.5 GB | Too big | — | |
| Q4_K_M | Good, most popular | 46.1 GB | Too big | — | |
| Q3_K_M | Noticeably degraded | 37.8 GB | Too big | — | |
| Q2_K | Heavily degraded | 29.8 GB | Too big | — |
GPUs that run Llama 3.1 70B comfortably
Frequently asked questions
Can NVIDIA RTX 4090 run Llama 3.1 70B?
No. Even at Q4_K_M, Llama 3.1 70B needs about 46.1 GB, but the NVIDIA RTX 4090 has 24 GB usable. You could offload some layers to system RAM, but it will be very slow.
How much VRAM does Llama 3.1 70B need?
About 46.1 GB at Q4_K_M with 8,192 tokens of context, and about 144.5 GB at full FP16 precision.
How fast is Llama 3.1 70B on the NVIDIA RTX 4090?
It does not fit in the NVIDIA RTX 4090's memory, so most layers would run from system RAM and generation would be very slow.