A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge the model - [mergek…
Model details →Goliath 120B vs Google: Gemma 2 27B
Google: Gemma 2 27B wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of text generation tasks, including question answering, sum…
Model details →Side-by-side comparison
| Capability | Goliath 120B | Google: Gemma 2 27B | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 6K | 8K | 🏆 Google: Gemma 2 27B |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.75 | $0.65 | 🏆 Google: Gemma 2 27B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $7.50 | $0.65 | 🏆 Google: Gemma 2 27B |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Goliath 120B better than Google: Gemma 2 27B?
Google: Gemma 2 27B wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Goliath 120B and Google: Gemma 2 27B?
Input: $3.75 vs $0.65 per 1M tokens. Output: $7.50 vs $0.65 per 1M tokens.
What context windows do Goliath 120B and Google: Gemma 2 27B support?
Goliath 120B supports up to 6K tokens. Google: Gemma 2 27B supports up to 8K tokens.
Do both Goliath 120B and Google: Gemma 2 27B support tool calling?
Goliath 120B: not advertised. Google: Gemma 2 27B: not advertised.