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 DeepSeek: R1 Distill Llama 70B
DeepSeek: R1 Distill Llama 70B wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techn…
Model details →Side-by-side comparison
| Capability | Goliath 120B | DeepSeek: R1 Distill Llama 70B | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 6K | 131K | 🏆 DeepSeek: R1 Distill Llama 70B |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.75 | $0.70 | 🏆 DeepSeek: R1 Distill Llama 70B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $7.50 | $0.80 | 🏆 DeepSeek: R1 Distill Llama 70B |
| 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. | — | Yes | 🏆 DeepSeek: R1 Distill Llama 70B |
Frequently asked questions
Is Goliath 120B better than DeepSeek: R1 Distill Llama 70B?
DeepSeek: R1 Distill Llama 70B wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Goliath 120B and DeepSeek: R1 Distill Llama 70B?
Input: $3.75 vs $0.70 per 1M tokens. Output: $7.50 vs $0.80 per 1M tokens.
What context windows do Goliath 120B and DeepSeek: R1 Distill Llama 70B support?
Goliath 120B supports up to 6K tokens. DeepSeek: R1 Distill Llama 70B supports up to 131K tokens.
Do both Goliath 120B and DeepSeek: R1 Distill Llama 70B support tool calling?
Goliath 120B: not advertised. DeepSeek: R1 Distill Llama 70B: not advertised.