Can RTX 5060 8GB run Llama-3.2-3B-Instruct?

NVIDIA · 8 GB GDDR7 · 448 GB/s bandwidth · Meta · 3.2B · model ctx up to 128K

Yes — the RTX 5060 8GB (8 GB GDDR7) can run Llama-3.2-3B-Instruct. At Q4 with the default 8K context it needs ≈ 3.4 GB VRAM (weights 1.76 GB + KV cache 0.64 GB + 1 GB runtime overhead), which fits within 8 GB. Decode at Q4/8K: ≈ 89.1 tok/s (estimated, batch 1). FP16 needs ≈ 8.04 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	3.08 GB	Yes	89.1 est.
Q4	8K default	3.4 GB	Yes	89.1 est.
Q4	32K	5.32 GB	Yes	89.1 est.
FP16	4K	7.72 GB	No	75.2 est.
FP16	8K default	8.04 GB	No	69.3 est.
FP16	32K	9.96 GB	No	45.2 est.

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 5060 8GB VRAM
Q4	1.76 GB	0.64 GB	1 GB	3.4 GB	8 GB
FP16	6.4 GB	0.64 GB	1 GB	8.04 GB	8 GB

Other GPUs that run Llama-3.2-3B-Instruct

• B200 192GB SXM — ≈1590.9 tok/s Q4 est.
• MI300X 192GB — ≈1054.0 tok/s Q4 est.
• H200 141GB SXM5 — ≈954.5 tok/s Q4 est.
• H100 80GB SXM5 — ≈666.2 tok/s Q4 est.
• Gaudi 3 128GB — ≈651.5 tok/s Q4 est.
• A100 80GB SXM4 — ≈405.5 tok/s Q4 est.
• RTX 5090 32GB — ≈356.4 tok/s Q4 est.
• RTX 4090 24GB — ≈200.5 tok/s Q4 est.

All GPUs for Llama-3.2-3B-Instruct →

Other models for the RTX 5060 8GB

• Qwen3-0.6B — ≈356.4 tok/s Q4 est.
• gemma-3-1b-it — ≈285.1 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈237.6 tok/s Q4 est.
• Qwen3-1.7B — ≈142.5 tok/s Q4 est.
• Phi-4-mini-instruct — ≈75.0 tok/s Q4 est.
• Phi-4-mini-reasoning — ≈75.0 tok/s Q4 est.
• gemma-3-4b-it — ≈73.1 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈71.3 tok/s Q4 est.

All models on the RTX 5060 8GB →