Can a Desktop CPU, DDR5 dual-channel (32GB) run Llama 3.2 3B?

Just about — Llama 3.2 3B runs at Q4_K_M (2.0 GB) at about 11–16 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

How much memory does Llama 3.2 3B need?

Llama 3.2 3B needs about 3.3 GB at 4K context at its smallest quantization. A Desktop CPU, DDR5 dual-channel (32GB) has 32.0 GB.

Tight fit: Llama 3.2 3B on a Desktop CPU, DDR5 dual-channel (32GB) at Q4_K_M

Yes, but it's tight.

Tight / slow

Best fit: Llama 3.2 3B at Q4_K_M · 2.0 GB weights · 11–16 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Arena Text Overall · style-controlled

1,167Q4_K_M untested

llama-3.2-3b-instruct · published configuration reference · Q4_K_M not tested

Arena Text Overall (style-controlled), exact published entry llama-3.2-3b-instruct, 2026-10-08: reference rating 1,166.8. Published confidence bounds 1,159.1–1,174.5. 7,936 votes. Published llama-3.2-3b-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 Q4_K_M 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: 3.3 GB; Weights + KV cache + runtime overhead
Estimated generation: 11–16 tok/s
Estimated first token: ~42s

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 3.2 3B quantizations on Desktop CPU, DDR5 dual-channel (32GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q4_K_M	2.0 GB	3.3 GB	11–16 tok/s	Tight / slow
Q5_K_M	2.3 GB	3.6 GB	10–15 tok/s	Tight / slow
Q6_K	2.6 GB	3.9 GB	9–14 tok/s	Tight / slow
Q8_0	3.4 GB	4.7 GB	7–11 tok/s	Tight / slow
FP16	6.4 GB	7.7 GB	4–7 tok/s	Tight / slow

Open the full calculator →Everything a Desktop CPU, DDR5 dual-channel (32GB) runs Llama 3.2 3B on other machines What to buy to run it →

Ran Llama 3.2 3B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →