Ollama Library · llama
Can I run yarn-llama2?
An extension of Llama 2 that supports a context of up to 128k tokens.
7B parameters64K contexttext24 builds
yarn-llama2 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 |
|---|---|---|---|
| yarn-llama2:7b | Q4_0 | 3.6 GB | ~5.5 GB(est.) |
| yarn-llama2:7b-128k-q4_0 | Q4_0 | 3.6 GB | ~5.5 GB(est.) |
| yarn-llama2:7b-64k-q4_K_M | Q4_K_M | 3.8 GB | ~5.8 GB(est.) |
| yarn-llama2:7b-128k-q4_K_M | Q4_K_M | 3.8 GB | ~5.8 GB(est.) |
| yarn-llama2:7b-64k-q5_K_M | Q5_K_M | 4.5 GB | ~6.8 GB(est.) |
| yarn-llama2:7b-128k-q5_K_M | Q5_K_M | 4.5 GB | ~6.8 GB(est.) |
| yarn-llama2:7b-64k-q6_K | Q6_K | 5.1 GB | ~7.8 GB(est.) |
| yarn-llama2:7b-128k-q6_K | Q6_K | 5.1 GB | ~7.8 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 yarn-llama2 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run yarn-llama2:7b - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about yarn-llama2
- How much VRAM do I need to run yarn-llama2?
- At 4K context, the smallest published build of yarn-llama2 (Q4_0) needs roughly 5.5 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 yarn-llama2 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 5.5 GB of free RAM for the smallest build.
- How big is the yarn-llama2 download?
- The smallest published build is 3.6 GB. There are 24 builds in total, the largest being 24.2 GB. Leave some extra free disk space beyond the download itself.
- How do I run yarn-llama2 locally?
- Install Ollama, then run "ollama run yarn-llama2:7b" in a terminal. The weights download on first use and an interactive session opens.
Will yarn-llama2 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