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 Meta: Llama 3 70B Instruct
Meta: Llama 3 70B Instruct wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source m…
Model details →Side-by-side comparison
| Capability | Goliath 120B | Meta: Llama 3 70B Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 6K | 8K | 🏆 Meta: Llama 3 70B Instruct |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.75 | $0.51 | 🏆 Meta: Llama 3 70B Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $7.50 | $0.74 | 🏆 Meta: Llama 3 70B Instruct |
| 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 Meta: Llama 3 70B Instruct?
Meta: Llama 3 70B Instruct 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 Meta: Llama 3 70B Instruct?
Input: $3.75 vs $0.51 per 1M tokens. Output: $7.50 vs $0.74 per 1M tokens.
What context windows do Goliath 120B and Meta: Llama 3 70B Instruct support?
Goliath 120B supports up to 6K tokens. Meta: Llama 3 70B Instruct supports up to 8K tokens.
Do both Goliath 120B and Meta: Llama 3 70B Instruct support tool calling?
Goliath 120B: not advertised. Meta: Llama 3 70B Instruct: not advertised.