Can RTX 3090 24GB run Llama-3.3-70B-Instruct?

NVIDIA · 24 GB GDDR6X · 936 GB/s bandwidth · Meta · 70.6B · model ctx up to 128K

No — Llama-3.3-70B-Instruct at Q4 needs ≈ 46.83 GB even at 4K context, beyond the RTX 3090 24GB's 24 GB GDDR6X. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 4.8 tok/s (estimated, batch 1). FP16 needs ≈ 156.2 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	46.83 GB	No	6.4 est.
Q4	8K default	53.83 GB	No	4.8 est.
Q4	32K	95.83 GB	No	1.5 est.
FP16	4K	149.2 GB	No	—
FP16	8K default	156.2 GB	No	—
FP16	32K	198.2 GB	No	—

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	RTX 3090 24GB VRAM
Q4	38.83 GB	14.0 GB	1 GB	53.83 GB	24 GB
FP16	141.2 GB	14.0 GB	1 GB	156.2 GB	24 GB

Other GPUs that run Llama-3.3-70B-Instruct

• B200 192GB SXM — ≈72.7 tok/s Q4 est.
• MI300X 192GB — ≈48.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈43.6 tok/s Q4 est.
• H100 80GB SXM5 — ≈30.5 tok/s Q4 est.
• Gaudi 3 128GB — ≈29.8 tok/s Q4 est.
• A100 80GB SXM4 — ≈18.5 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — ≈7.4 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈7.3 tok/s Q4 est.

All GPUs for Llama-3.3-70B-Instruct →

Other models for the RTX 3090 24GB

• Qwen3-0.6B — ≈744.5 tok/s Q4 est.
• gemma-3-1b-it — ≈595.6 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈496.4 tok/s Q4 est.
• Qwen3-1.7B — ≈297.8 tok/s Q4 est.
• Qwen3-30B-A3B — ≈198.5 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈198.5 tok/s Q4 est.
• GLM-4.7-Flash — ≈198.5 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈198.5 tok/s Q4 est.

All models on the RTX 3090 24GB →