Can RTX 3080 10GB run gemma-3-27b-it?

NVIDIA · 10 GB GDDR6X · 760 GB/s bandwidth · google · 27.4B · model ctx up to NoneK

CUDA

No — gemma-3-27b-it at Q4 needs ≈ 18.81 GB even at 4K context, beyond the RTX 3080 10GB's 10 GB GDDR6X. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 10.8 tok/s (estimated, batch 1). FP16 needs ≈ 61.28 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	18.81 GB	No	14.2 ± est.
Q4	8K default	21.55 GB	No	10.8 ± est.
Q4	32K	37.99 GB	No	3.5 ± est.
FP16	4K	58.54 GB	No	—
FP16	8K default	61.28 GB	No	—
FP16	32K	77.72 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 3080 10GB VRAM
Q4	15.07 GB	5.48 GB	1 GB	21.55 GB	10 GB
FP16	54.8 GB	5.48 GB	1 GB	61.28 GB	10 GB

Other GPUs that run gemma-3-27b-it

• B200 192GB SXM — ≈185.8 tok/s Q4 est.
• MI300X 192GB — ≈123.1 tok/s Q4 est.
• H200 141GB SXM5 — ≈111.5 tok/s Q4 est.
• H100 80GB SXM5 — ≈77.8 tok/s Q4 est.
• Gaudi 3 128GB — ≈76.1 tok/s Q4 est.
• A100 80GB SXM4 — ≈47.4 tok/s Q4 est.
• RTX 5090 32GB — ≈41.6 tok/s Q4 est.
• RTX 4090 24GB — ≈23.4 tok/s Q4 est.

All GPUs for gemma-3-27b-it →

Other models for the RTX 3080 10GB

• MiniCPM5-1B — ≈447.8 tok/s Q4 est.
• Qwen3.5-2B — ≈241.8 tok/s Q4 est.
• DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx — ≈210.3 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈151.1 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈120.9 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈120.9 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈120.9 tok/s Q4 est.
• gemma-4-E2B-it — ≈94.8 tok/s Q4 est.

All models on the RTX 3080 10GB →