Ollama Library · llama
Can I run goliath?
A language model created by combining two fine-tuned Llama 2 70B models into one.
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 contextgoliath 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 |
|---|---|---|---|
| goliath:120b-q4_0120B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 61.8 GB | ~69.2 GB |
| goliath:120b-q4_K_M120B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 65.8 GB | ~73.6 GB |
| goliath:120b-q5_K_M120B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 77.5 GB | ~86.2 GB |
| goliath:120b-q6_K120B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q6_K | 90.0 GB | ~99.7 GB |
| goliath:120b-q8_0120B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 116.5 GB | ~128.4 GB |
| goliath:120b-fp16120B parameters (tag)4K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 219.3 GB | ~239.4 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 goliath locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull goliath:120b-q4_0 - 3.Check the source for the build's task. For text generation, run
ollama run goliath:120b-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 goliath
- How much VRAM do I need to run goliath?
- At 4K context, the smallest published build of goliath (Q4_0) needs roughly 69.2 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 goliath without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 69.2 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 goliath download?
- The smallest published build is 61.8 GB. There are 6 builds in total, the largest being 219.3 GB. Leave some extra free disk space beyond the download itself.
- How do I run goliath locally?
- Install Ollama, then download a specific build with "ollama pull goliath:120b-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 goliath 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