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 Mancer: Weaver (alpha)
Mancer: Weaver (alpha) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.
Model details →Side-by-side comparison
| Capability | Goliath 120B | Mancer: Weaver (alpha) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 6K | 8K | 🏆 Mancer: Weaver (alpha) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.75 | $0.75 | 🏆 Mancer: Weaver (alpha) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $7.50 | $1.00 | 🏆 Mancer: Weaver (alpha) |
| 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 Mancer: Weaver (alpha)?
Mancer: Weaver (alpha) 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 Mancer: Weaver (alpha)?
Input: $3.75 vs $0.75 per 1M tokens. Output: $7.50 vs $1.00 per 1M tokens.
What context windows do Goliath 120B and Mancer: Weaver (alpha) support?
Goliath 120B supports up to 6K tokens. Mancer: Weaver (alpha) supports up to 8K tokens.
Do both Goliath 120B and Mancer: Weaver (alpha) support tool calling?
Goliath 120B: not advertised. Mancer: Weaver (alpha): not advertised.