Can the RTX 4090 run Llama 3.1 8B?
Yes. Llama 3.1 8B fits the RTX 4090's 24 GB at Q4_K_M (about 7.3 GB needed), running at an estimated 114 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Llama 3.1 8B (8B) on 24 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 5.5 GB | 7.3 GB | Fits easily | ~114 tok/s |
| Q5_K_M | 7 GB | 8.8 GB | Fits easily | ~89 tok/s |
| Q8_0 | 10 GB | 11.8 GB | Fits easily | ~63 tok/s |
| FP16 | 16 GB | 17.8 GB | Fits | ~39 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 4090's 1008 GB/s bandwidth (XiongjieDai/GPU-Benchmarks-on-LLM-Inference). Long contexts need more memory and run slower.
Run it
Copy, paste, go
ollama run llama3.1:8bllama-server -hf bartowski/Meta-Llama-3.1-8B-Instruct-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Llama 3.1 8B details →
Compare
Same model, other hardware - and other models on this card
Llama 3.1 8B on other hardware
- RTX 5090~187 tok/s
- RTX 5090 D~187 tok/s
- RTX 6000D~164 tok/s
- RTX 3090~100 tok/s
- Radeon RX 7900 XTX~100 tok/s
- RTX 5080~100 tok/s
- RTX 3080 Ti~95 tok/s
- RTX 5080 Mobile~93 tok/s
Also runs on the RTX 4090
- GLM-4.7-Flash~241 tok/s
- Qwen3-30B-A3B-Instruct-2507~236 tok/s
- Qwen3.6 27B~39 tok/s
- Qwen3.8 27B~39 tok/s
- Gemma 4 26B A4B~184 tok/s
- gpt-oss-20b~208 tok/s
- Qwen2.5-Coder-14B-Instruct~70 tok/s
- Qwen3 14B~78 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 4090 run Llama 3.1 8B?
Yes. Llama 3.1 8B fits the RTX 4090's 24 GB at Q4_K_M (about 7.3 GB needed), running at an estimated 114 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Llama 3.1 8B need?
About 5.5 GB of weights at Q4_K_M, 10 GB at Q8_0 and 16 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Llama 3.1 8B on the RTX 4090?
Roughly 114 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 4090's 1008 GB/s memory bandwidth.