on

Can the NVIDIA Quadro RTX 8000 run DeepSeek R1 Distill Llama 70B?

60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well

Runs well. At Q3_K_M it needs about 40.3 GB of 48.0 GB usable, with an estimated speed of 15.1 tok/s.

Best quant
Q3_K_M
Generation speed
15.1 tok/s
Prompt processing
166 tok/s
First token (1K prompt)
6.2 s
Largest safe context
31K

Best app to run it on the NVIDIA Quadro RTX 8000

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run deepseek-r1:70b
  • LM Studio Point-and-click: search, download and chat in one window.
  • llama.cpp Usually the first to support new model architectures.

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

  • One command with Ollama’s own build of this model.
  • Serves an OpenAI-compatible API that other apps and coding tools can use.
ollama run deepseek-r1:70b
  • LM Studio Point-and-click: search, download and chat in one window.
  • llama.cpp Usually the first to support new model architectures.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download DeepSeek R1 Distill Llama 70B

Recommended for the NVIDIA Quadro RTX 8000: Q3_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run deepseek-r1:70b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q3_K_M file (opens in a new tab)

huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF:Q3_K_M

Original weights · Hugging Face

Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.

huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from DeepSeek. The weights themselves download from Hugging Face.

github.com/deepseek-ai/DeepSeek-R1 (opens in a new tab)

The R1 repo covers the distilled models too.

git clone https://github.com/deepseek-ai/DeepSeek-R1

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q3_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well
How well it runs on the NVIDIA Quadro RTX 8000: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.27.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.9.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Match score76.4 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA Quadro RTX 8000

Quant Memory needed Available Speed Runs Quality Download
Q2_K 33.9 GB 48.0 GB 19.2 tok/s Runs well 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 40.3 GB 48.0 GB 15.1 tok/s Runs well 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 48.7 GB 48.0 GB 10.2 tok/s Runs welloffloads to RAM 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 55.8 GB 48.0 GB 4.0 tok/s Slowoffloads to RAM 69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 63.5 GB 48.0 GB 2.4 tok/s Very slowoffloads to RAM 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q8_0 80.5 GB 48.0 GB — Won't run 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
F16 147 GB 48.0 GB — Won't run 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does DeepSeek R1 Distill Llama 70B need on the NVIDIA Quadro RTX 8000 48GB?

At Q3_K_M it needs about 40.3 GB. The NVIDIA Quadro RTX 8000 48GB has 48.0 GB usable.

How fast is DeepSeek R1 Distill Llama 70B on the NVIDIA Quadro RTX 8000 48GB?

About 15.1 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek R1 Distill Llama 70B should I use on the NVIDIA Quadro RTX 8000 48GB?

Q3_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?