Re:MythoMax Models by Undi95
Last refreshed 2026-05-19. Next refresh: weekly.
Details
Capabilities
Links
HuggingFaceAbout
The Re:MythoMax (ReMM) family of large language models are enhanced recreations of the original MythoMax model, integrating the sophisticated SLERP merging technique. Rooted in the MythoMax-L2-B13 model, these updated models leverage newer base architectures to deliver improved performance 45. By combining elements from ReML, a recreation of MythoLogic-L2-13B, and Huginn v1.2, ReMM models benefit from a robust and versatile underlying design 45. The family includes versions like ReMM v2 and ReMM v2.2, demonstrating continuous refinement and enhancement in their generation capabilities. These models are accessible in fp16 format on Hugging Face, supporting various applications with their innovative and adaptive framework 45.
Decision facts
- Best fit
- structured outputs
- Capability starting point
- ReMM SLERP L2 13B with 4k context and structured outputs
- Lowest tracked input
- ReMM SLERP L2 13B · $0.3/1M · Together AI
- Closest related family
- Toppy
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 4k context, 13B parameters, and structured outputs.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| ReMM SLERP L2 13B | Use when the workload needs 4k context, 13B parameters, and structured outputs. | 2023-12 | 4k context13B parametersstructured outputs | Current |
Release Timeline
1 release groupSpecifications(1 models)
| Model | Released | Context | Parameters | Structured Outputs |
|---|---|---|---|---|
| ReMM SLERP L2 13B | 2023-12 | 4k | 13B | Yes |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| ReMM SLERP L2 13B | Together AI | $0.3 | $0.3 | Serverless |
| ReMM SLERP L2 13B | OpenRouter | $0.45 | $0.65 | Serverless |
