Can the NVIDIA RTX 4090 run Llama 3.1 8B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
Yes. The NVIDIA RTX 4090 can run Llama 3.1 8B fully in VRAM at FP16 (full quality), using about 17.7 GB of the 24 GB available, at roughly 38 tokens/second.
Run it with Ollama
With Ollama installed, one command downloads and starts Llama 3.1 8B:
ollama run llama3.1:8bOllama's default download is Q4_K_M (about 6.5 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.
New to this? Step-by-step setup for the RTX 4090
Run it in the cloud
No NVIDIA RTX 4090? Run Llama 3.1 8B in the cloud.
Rent a cloud GPU by the hour. No upfront cost, stop any time.
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 | 17.7 GB | Fits | ~38 tok/s | |
| Q8_0 | Near-lossless | 10.2 GB | Fits | ~71 tok/s | |
| Q6_K | Excellent | 8.3 GB | Fits | ~92 tok/s | |
| Q5_K_M | Very good | 7.4 GB | Fits | ~106 tok/s | |
| Q4_K_M | Good, most popular | 6.5 GB | Fits | ~124 tok/s | |
| Q3_K_M | Noticeably degraded | 5.6 GB | Fits | ~154 tok/s | |
| Q2_K | Heavily degraded | 4.7 GB | Fits | ~201 tok/s |
GPUs that run Llama 3.1 8B comfortably
Frequently asked questions
Can NVIDIA RTX 4090 run Llama 3.1 8B?
Yes. The NVIDIA RTX 4090 can run Llama 3.1 8B fully in VRAM at FP16 (full quality), using about 17.7 GB of the 24 GB available, at roughly 38 tokens/second.
How much VRAM does Llama 3.1 8B need?
About 6.5 GB at Q4_K_M with 8,192 tokens of context, and about 17.7 GB at full FP16 precision.
How fast is Llama 3.1 8B on the NVIDIA RTX 4090?
Roughly 38 tokens per second at FP16, estimated from the NVIDIA RTX 4090's 1008 GB/s memory bandwidth.