Llama 3.1 8B (about 6 GB at Q4_K_M with 8k context, estimated) fits on 8–12 GB GPUs; Llama 3.3 70B needs about 46 GB at 4-bit (estimate), so two 24 GB cards or a 128 GB unified-memory system; 405B is beyond single consumer machines.
| Model | Params (total / active) | Est. memory, Q4 @ 8k ctx | Est. memory, Q8 @ 8k ctx | Cheapest fit in our data (Q4) |
|---|---|---|---|---|
| Llama 3.1 8B | 8.03B / 8.03B | 7.0 GB | 10.6 GB | GeForce RTX 5060 ($299, GPU launch MSRP) |
| Llama 3.3 70B | 70.6B / 70.6B | 46.8 GB | 78.7 GB | GMKtec EVO-X2 (128GB / 1TB) ($3,499.99, system, listed price) |
| Llama 3.1 405B | 405.9B / 405.9B | 253.3 GB | 436.5 GB | No single device in our dataset |
Parameter counts: Hugging Face: meta-llama/Llama-3.1-8B; Hugging Face: meta-llama/Llama-3.3-70B-Instruct; Hugging Face: meta-llama/Llama-3.1-405B. Memory figures are our estimates (see methodology), not measurements.
Check your own hardware
Can My PC Run It?
Loading…