Ollama Library · qwen2
Can I run athene-v2?
Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.
Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.
Calculate memory for a build and contextathene-v2 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 |
|---|---|---|---|
| athene-v2:72b-q4_072B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 38.4 GB | ~43.1 GB |
| athene-v2:72b72B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 44.2 GB | ~49.3 GB |
| athene-v2:72b-q5_K_M72B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 50.7 GB | ~56.4 GB |
| athene-v2:72b-q6_K72B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 59.9 GB | ~66.4 GB |
| athene-v2:72b-q8_072B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 72.0 GB | ~79.4 GB |
| athene-v2:72b-fp1672B parameters (tag)32K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 135.4 GB | ~147.9 GB |
Showing the 6 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.
How to run athene-v2 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull athene-v2:72b-q4_0 - 3.Check the source for the build's task. For text generation, run
ollama run athene-v2:72b-q4_0. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about athene-v2
- How much VRAM do I need to run athene-v2?
- At 4K context, the smallest published build of athene-v2 (Q4_0) needs roughly 43.1 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 athene-v2 without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 43.1 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
- How big is the athene-v2 download?
- The smallest published build is 38.4 GB. There are 6 builds in total, the largest being 135.4 GB. Leave some extra free disk space beyond the download itself.
- How do I run athene-v2 locally?
- Install Ollama, then download a specific build with "ollama pull athene-v2:72b-q4_0". For a build that supports text generation, use ollama run with the same tag. Check the model source for its task and prompt format.
Will athene-v2 run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Compare with similar models
Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.
Model data from the official Ollama registry · verified 13/10/2026