Can you run Llama 3.3 70B Instruct on RTX 5090?
Llama 3.3 70B Instruct Q4_K_M on the NVIDIA GeForce RTX 5090 — verdict, VRAM math and estimated speed.
Yes, but slowly — Llama 3.3 70B Instruct spills past the RTX 5090. 42 GB weights at Q4_K_M vs 28.8 GB usable VRAM; ~5 tok/s est..
VRAM math and speed are ModelFit engine estimates, not measurements. Commands are registry-verified Ollama tags.
Cite this page: ModelFit, Llama 3.3 70B Instruct on RTX 5090, https://modelfit.io/can-i-run/llama3.3-70b-q4-on-rtx-5090/, updated August 2026, CC BY 4.0.
Last updated: August 16, 2026 · Editor: ModelFit Team
Memory math: weights + context vs budget
Weights take 42 GB. Context costs extra KV-cache on top — this is where long-context sessions break on cards that technically fit the weights.
KV-cache figures assume an fp16 cache, the llama.cpp/Ollama default. Standard GQA models use a size-class estimate (8 KV heads x 128 head dim class); hybrid linear-attention models (Qwen3.5/3.6, Qwen3-Next) use the exact per-token cost from their published config, since only their sparse full-attention layers cache KV. A q8_0 KV cache roughly halves either figure. Estimates, not measurements.
Try a different quant
Upgrade path
The cheapest tracked card that runs Llama 3.3 70B Instruct comfortably is the NVIDIA RTX PRO 6000 Blackwell (96 GB VRAM).
See the RTX PRO 6000 pageLlama 3.3 70B Instruct on RTX 5090: FAQ
Can the NVIDIA GeForce RTX 5090 run Llama 3.3 70B Instruct?
Barely. Llama 3.3 70B Instruct (Q4_K_M) needs about 42 GB but the RTX 5090 has 28.8 GB usable VRAM, so part of the model spills to system RAM and speed drops to at roughly 5 tokens/sec (est.).
How much VRAM does Llama 3.3 70B Instruct need?
About 42 GB for the weights at Q4_K_M, plus KV-cache for context: roughly 5.0 GB extra at 16k tokens. The RTX 5090 budget is 28.8 GB (32 GB x 90%).
What is the best quantization of Llama 3.3 70B Instruct for the RTX 5090?
Stick with the Q4_K_M build at 42 GB — every heavier quant exceeds the 28.8 GB usable VRAM.
What GPU do I need to run Llama 3.3 70B Instruct comfortably?
The cheapest tracked card that runs Llama 3.3 70B Instruct (Q4_K_M) fully in VRAM is the NVIDIA RTX PRO 6000 Blackwell (96 GB).