How much memory does DeepSeek-R1-Distill 70B need at Q4?

About 45.8 GB at 8,192 tokens (estimate): 42.4 GB weights, 2.7 GB KV cache, 0.8 GB overhead.

How fast is DeepSeek-R1-Distill 70B on Dual RTX 4090 (estimate)?

About 19.1 tok/s at Q4 (estimate, not a benchmark).

estimate

Can I run DeepSeek-R1-Distill 70B on a Dual RTX 4090?

Yes, fully in VRAM (estimate)

Can I run DeepSeek-R1-Distill 70B on a Dual RTX 4090? Yes, fully in VRAM (estimate). About 45.8 GB at Q4_K_M (estimate).

Updated 2026-10-16. The later of the hardware price date and the formula date.

DeepSeek-R1-Distill 70B on Dual RTX 4090, formula estimate
Quant	Context	Weights	KV	Overhead	Total	Usable	Fit	Est. tok/s
Q4 Q4_K_M	8,192 tokens	42.4 GB estimate	2.7 GB estimate	0.8 GB estimate	45.8 GB estimate	46.8 GB estimate	full	19.1 tok/s estimate
Q5 Q5 (~0.71 bytes/param)	8,192 tokens	50.1 GB estimate	2.7 GB estimate	0.8 GB estimate	53.6 GB estimate	46.8 GB estimate	offload	4.9 tok/s estimate
Q8 Q8	8,192 tokens	75.5 GB estimate	2.7 GB estimate	0.8 GB estimate	79.0 GB estimate	46.8 GB estimate	offload	1.2 tok/s estimate
FP16 FP16	8,192 tokens	141.2 GB estimate	2.7 GB estimate	0.8 GB estimate	144.7 GB estimate	46.8 GB estimate	offload	0.4 tok/s estimate
Q4, longer context	32,768 tokens	42.4 GB estimate	10.7 GB estimate	0.8 GB estimate	53.9 GB estimate	46.8 GB estimate	offload	4.8 tok/s estimate

Formula estimate, not a benchmark. Method →

Cheapest catalog option that fits at Q4

Mac mini M4 Pro 64GB, catalog price, €1,890, dated 2026-10-16. No buy link.

This hardware

$8,206€7,330

price as of 16 Oct 2026

128 GB DDR4 (estimate): $2,754€2,460. From the 16 Oct 2026 fact-check.

rest of system (estimate): $560€500. The total is the GPU price plus the RAM line plus this estimate. It is not a checked system price.

price unverified

GPU line is 2× the used median €2,185 (€4,370), labelled used, from pcprice.watch (https://www.pcprice.watch/gpu-buying-guide/rtx-4090-price-used-and-specs). 128 GB DDR4 (estimate) €2,460, from the 16 Oct 2026 fact-check. Rest of system (estimate) €500. Other parts from €500 in that fact-check. Not a shop listing. DDR5 was not separately priced, so this total uses the sourced 128 GB DDR4 line. The total is the GPU price plus the RAM line plus that rest estimate. It is not a checked system price.

Embed this

DeepSeek-R1-Distill 70B on Dual RTX 4090

[![DeepSeek-R1-Distill 70B Q4 on Dual RTX 4090: fits ✓ · est. 19.1 tok/s (estimate)](https://localllmrig.com/badge/deepseek-r1-distill-70b/dual-rtx-4090.svg)](https://localllmrig.com/can-i-run/deepseek-r1-distill-70b/dual-rtx-4090?utm_source=badge)

Questions

Can I run DeepSeek-R1-Distill 70B on a Dual RTX 4090?: Yes, fully in VRAM (estimate).
How much memory does DeepSeek-R1-Distill 70B need at Q4?: About 45.8 GB at 8,192 tokens (estimate): 42.4 GB weights, 2.7 GB KV cache, 0.8 GB overhead.
How fast is DeepSeek-R1-Distill 70B on Dual RTX 4090 (estimate)?: About 19.1 tok/s at Q4 (estimate, not a benchmark).