No — not on this device

DeepSeek-R1-Distill-Llama 70B at Q4_K_M needs 42.8 GB against 9.7 GB usable, and the shortfall of 33.1 GB is more than 16 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 39.7 GB MIT / Llama 3.3 Community Released Jan 2025

The strongest of the R1 distills, and the one that most needs 48 GB or more.

Hardware requirements What hardware do I need to run DeepSeek-R1-Distill-Llama 70B? →

At Q4_K_M with an 8K context: a 64 GB GPU (Instinct MI210) or a 96 GB Mac (M2 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

Fits instead: DeepSeek-R1-Distill-Qwen 7B (5.3 GB)

The VRAM budget

weights 39.7 GB
Weights 39.7 GB KV cache @ 8K 2.50 GB Runtime overhead 0.6 GB Over budget 33.1 GB past 9.7 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 69.9 GB 73.0 GB — ~0.6 −0.1% ppl 63.3 GB over
Q6_K 53.9 GB 57.0 GB — ~0.8 −0.4% ppl 47.3 GB over
Q5_K_M 46.6 GB 49.7 GB — ~0.9 −0.8% ppl 40.0 GB over
Q4_K_M 39.7 GB 42.8 GB — ~1.1 −1.9% ppl 33.1 GB over
Q3_K_M 32.1 GB 35.2 GB — ~1.4 −5.4% ppl 25.5 GB over
Q2_K 27.5 GB 30.6 GB — ~1.7 −15% ppl 20.9 GB over

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ llama-server \
    -hf deepseek-ai/DeepSeek-R1-Distill-Llama-70B:Q4_K_M \
    -c 8192 -ngl 13

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 39.7 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on a GeForce RTX 2080 Ti

ModelTotalTok/s est.
DeepSeek-R1-Distill-Qwen 32B
32.8B · same family
Q4_K_M · 21.0 GB ~3.0 CPU offload
DeepSeek-R1-Distill-Qwen 14B
14.8B · same family
Q4_K_M · 10.4 GB ~25 CPU offload
DeepSeek-R1-Distill-Qwen 7B
7.62B · same family
Q4_K_M · 5.3 GB 87 Runs great
DeepSeek-R1 671B
671B MoE · same family
Q4_K_M · 378.4 GB — Won't fit
Llama 3.3 70B Instruct
70.6B · similar size
Q4_K_M · 42.8 GB — Won't fit
Llama 4 Scout 109B-A17B
109B MoE · similar size
Q4_K_M · 63.4 GB — Won't fit
gpt-oss 120B
117B MoE · similar size
MXFP4 · 61.4 GB — Won't fit

Every model against the GeForce RTX 2080 Ti →

DeepSeek-R1-Distill-Llama 70B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
42.8 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
42.8 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
42.8 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
42.8 GB — Won't fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
42.8 GB — Won't fit
Instinct MI210
62.4 GB usable · 1638 GB/s
42.8 GB 25 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
42.8 GB 5.6 Tight fit
M2 Max · 96 GB
72.0 GB usable · 400 GB/s
42.8 GB 5.6 Runs great

All 114 devices, by tier →