Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Llama 3.3 70B Instruct?

Yes — Llama 3.3 70B Instruct runs at Q8_0 (75.0 GB) at about 42–63 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

How much memory does Llama 3.3 70B Instruct need?

Llama 3.3 70B Instruct needs about 28.5 GB at 4K context at its smallest quantization. A NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) has 144.0 GB.

Yes — Llama 3.3 70B Instruct runs on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) at Q8_0

Yes — it runs great.

Runs great

Best fit: Llama 3.3 70B Instruct at Q8_0 · 75.0 GB weights · 42–63 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Arena Text Overall · style-controlled

1,318Q8_0 untested

llama-3.3-70b-instruct · published configuration reference · Q8_0 not tested

Arena Text Overall (style-controlled), exact published entry llama-3.3-70b-instruct, 2026-10-08: reference rating 1,318. Published confidence bounds 1,314.5–1,321.5. 54,504 votes. Published llama-3.3-70b-instruct configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q8_0 has not been measured by this Arena entry. No quantization quality adjustment is applied.

Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh

Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986

Total memory at 4K context: 77.1 GB; Weights + KV cache + runtime overhead
Estimated generation: 42–63 tok/s
Estimated first token: ~3.2s

Every quantization on this machine

On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.

Llama 3.3 70B Instruct quantizations on NVIDIA GH200 Grace Hopper (144GB HBM + 480GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	26.4 GB	28.5 GB	96–144 tok/s	Runs great
Q3_K_M	34.3 GB	36.4 GB	80–119 tok/s	Runs great
Q4_K_M	42.5 GB	44.7 GB	67–101 tok/s	Runs great
Q5_K_M	50.0 GB	52.1 GB	59–89 tok/s	Runs great
Q6_K	57.9 GB	60.0 GB	52–79 tok/s	Runs great
Q8_0	75.0 GB	77.1 GB	42–63 tok/s	Runs great
FP16	141.1 GB	143.3 GB	12–17 tok/s	Tight / slow

Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runs Llama 3.3 70B Instruct on other machines What to buy to run it →

Ran Llama 3.3 70B Instruct on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →