ELYZA Japanese Llama 2 Models by ELYZA
Last refreshed 2026-05-19. Next refresh: weekly.
Details
About
The ELYZA Japanese Llama 2 family of LLMs is an adaptation of Meta's Llama 2, tailored specifically for enhanced Japanese language processing. By leveraging Llama 2's extensive English pre-training, ELYZA effectively integrates additional pre-training on Japanese text. This strategy optimizes performance by utilizing a robust base model and augmenting it with Japanese language capabilities. Available in various parameter sizes, such as 7B and 13B, these models include special "instruct" versions designed for instruction-following tasks. They are built to handle diverse natural language processing applications such as text generation, question answering, and translation, while also being accessible for both commercial and research purposes. The "fast" variants prioritize speed, whereas "instruct" versions are fine-tuned for superior instruction adherence.
Decision facts
- Best fit
- General model comparison
- Capability starting point
- ELYZA Japanese Llama 2 7B
- Lowest tracked input
- ELYZA Japanese Llama 2 7B · $0.2/1M · Fireworks AI
- Closest related family
- ELYZA Japanese CodeLlama
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| ELYZA Japanese Llama 2 7B | Use when the workload needs 7B parameters. | 2023-08 | 7B parameters | Current |
| ELYZA Japanese Llama 2 13B | Use when the workload needs 13B parameters. | 2023-08 | 13B parameters | Current |
| ELYZA Japanese Llama 3 8B | Use when the workload needs 8B parameters. | 2023-08 | 8B parameters | Current |
Release Timeline
1 release groupSpecifications(3 models)
| Model | Released | Parameters |
|---|---|---|
| ELYZA Japanese Llama 2 7B | 2023-08 | 7B |
| ELYZA Japanese Llama 2 13B | 2023-08 | 13B |
| ELYZA Japanese Llama 3 8B | 2023-08 | 8B |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| ELYZA Japanese Llama 2 7B | Fireworks AI | $0.2 | $0.2 | Provisioned |
| ELYZA Japanese Llama 2 7B | IBM watsonx | $1.8 | $1.8 | Serverless |
Popular comparisons in this family
- ELYZA Japanese Llama 2 7B vs Llama 2 7B215
- ELYZA Japanese Llama 2 13B vs Llama 3.1 Swallow 8B Instruct120
- ELYZA Japanese Llama 2 7B vs Llama 3 Swallow 70B Instruct103
- ELYZA Japanese Llama 2 7B vs Swallow 30B101
- ELYZA Japanese Llama 2 7B vs Llama 3.1 Swallow 8B Instruct97
- ELYZA Japanese Llama 2 7B vs GPT-184
- ELYZA Japanese Llama 2 7B vs Qwen3.5-9B80
- ELYZA Japanese Llama 2 13B vs Llama 3 Swallow 70B Instruct77
- ELYZA Japanese Llama 2 7B vs Qwen2-7B-Instruct67
- ELYZA Japanese Llama 2 13B vs Stockmark 2 100B Instruct58
