🛠️ Free Tools Hub 17 free tools · no signup

LLM VRAM requirements — quick reference

Approximate total VRAM (model weights + KV cache + overhead) to run a model at 8K context, computed with the same formula as the calculator above. Adjust the calculator for your exact model, quantization and context length.

Model sizeFP16Q8_0Q6_KQ4_K_M ★Smallest GPU (Q4_K_M)
3B7.8 GB5.0 GB4.3 GB3.6 GB8 GB
7B16.1 GB9.5 GB7.9 GB6.4 GB8 GB
8B18.2 GB10.7 GB8.7 GB7.1 GB8 GB
13B28.7 GB16.2 GB13.1 GB10.4 GB12 GB
14B30.9 GB17.3 GB14.0 GB11.0 GB12 GB
32B69.2 GB37.7 GB29.6 GB22.6 GB24 GB (RTX 4090)
70B149.8 GB80.7 GB63.1 GB47.6 GB48 GB
405B856 GB456 GB354 GB265 GBmulti-GPU

Q4_K_M (~4.85-bit) is the recommended quality/size sweet spot. Figures include a depth-calibrated KV cache and a small runtime buffer; longer context raises the KV cache. Open the calculator ↑ for exact numbers.

VRAM requirements by model

Exact per-model requirement pages — browse all models →

Llama 3.3 70B · Llama 3.1 8B · Qwen2.5 72B · Qwen2.5 Coder 32B · Qwen2.5 32B · DeepSeek-R1 671B · DeepSeek-R1 70B · Mixtral 8x7B · Gemma 2 27B · Phi-4 14B · Mistral 7B

How much VRAM to run Llama 3 70B?

About 48 GB in Q4_K_M (4-bit), 81 GB in Q8_0, or 150 GB in FP16 at 8K context. A 70B model fits on one 48 GB GPU (RTX 6000 Ada / Radeon PRO W7900) in 4-bit, or an 80 GB A100 in 8-bit.

Can I run a 32B model on a 24 GB GPU (RTX 4090)?

Yes — at Q4_K_M a 32B model needs ~23 GB, which just fits a 24 GB RTX 4090 / RX 7900 XTX at 8K context. Q6_K (~30 GB) and Q8_0 (~38 GB) need a larger card.

How much VRAM for a 7B model?

About 6.4 GB in Q4_K_M, 9.5 GB in Q8_0, and 16 GB in FP16 — a 7B model runs comfortably on an 8 GB GPU in 4-bit, so most modern laptops and entry GPUs can handle it.

📎 Embed this calculator (free)

Drop the VRAM calculator into your own blog or docs — paste this snippet: