Ollama Library · llama
Can I run r1-1776?
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
70.6B parameters128K contexttextMIT License6 builds
r1-1776 system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| r1-1776:70b | Q4_K_M | 39.6 GB | ~57.0 GB(est.) |
| r1-1776:70b-distill-llama-q8_0 | Q8_0 | 69.8 GB | ~100.2 GB(est.) |
| r1-1776:70b-distill-llama-fp16 | F16 | 131.4 GB | ~188.3 GB(est.) |
| r1-1776:671b | Q4_K_M | 376.7 GB | ~539.0 GB(est.) |
| r1-1776:671b-q8_0 | Q8_0 | 664.3 GB | ~950.3 GB(est.) |
| r1-1776:671b-fp16 | F16 | 1250.1 GB | ~1788.0 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run r1-1776 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run r1-1776:70b - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about r1-1776
- How much VRAM do I need to run r1-1776?
- At 4K context, the smallest published build of r1-1776 (Q4_K_M) needs roughly 57.0 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run r1-1776 without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 57.0 GB of free RAM for the smallest build.
- How big is the r1-1776 download?
- The smallest published build is 39.6 GB. There are 6 builds in total, the largest being 1250.1 GB. Leave some extra free disk space beyond the download itself.
- How do I run r1-1776 locally?
- Install Ollama, then run "ollama run r1-1776:70b" in a terminal. The weights download on first use and an interactive session opens.
Will r1-1776 run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026