Can a AMD Instinct MI355X (288GB) run Llama 3.3 70B Instruct?

Yes — Llama 3.3 70B Instruct runs at FP16 (141.1 GB) at about 37–56 tok/s on a AMD Instinct MI355X (288GB).

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 AMD Instinct MI355X (288GB) has 288.0 GB.

Yes — Llama 3.3 70B Instruct runs on a AMD Instinct MI355X (288GB) at FP16

Yes — it runs great.

Runs great

Best fit: Llama 3.3 70B Instruct at FP16 · 141.1 GB weights · 37–56 tok/s on a AMD Instinct MI355X (288GB).

Arena Text Overall · style-controlled

1,318FP16 untested

llama-3.3-70b-instruct · published configuration reference · FP16 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 FP16 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: 143.3 GB; Weights + KV cache + runtime overhead
Estimated generation: 37–56 tok/s
Estimated first token: ~1.7s

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 AMD Instinct MI355X (288GB), 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	135–202 tok/s	Runs great
Q3_K_M	34.3 GB	36.4 GB	114–171 tok/s	Runs great
Q4_K_M	42.5 GB	44.7 GB	99–148 tok/s	Runs great
Q5_K_M	50.0 GB	52.1 GB	88–131 tok/s	Runs great
Q6_K	57.9 GB	60.0 GB	78–118 tok/s	Runs great
Q8_0	75.0 GB	77.1 GB	64–96 tok/s	Runs great
FP16	141.1 GB	143.3 GB	37–56 tok/s	Runs great

Open the full calculator →Everything a AMD Instinct MI355X (288GB) runs Llama 3.3 70B Instruct on other machines What to buy to run it →

Ran Llama 3.3 70B Instruct on a AMD Instinct MI355X (288GB)? Add your real numbers →