Back
Goliath 120B
Llama2
Input: text
Output: text
Released: Nov 10, 2023•Updated: Mar 28, 2025
A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.
Credits to
- @chargoddard for developing the framework used to merge the model - mergekit.
- @Undi95 for helping with the merge ratios.
#merge
6,144 Token Context
Process and analyze large documents and conversations.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| Mancer (private) | mancer (private) | 6K | 1K | $10.00/M | $12.50/M | 17.5 t/s | 2015 ms |
Standard Pricing
Input Tokens
$0.00001
per 1K tokens
Output Tokens
$0.0000125
per 1K tokens