undi95
ReMM SLERP 13B
undi95/remm-slerp-l2-13b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
undi95/remm-slerp-l2-13b is a text-to-text Llama 2-based checkpoint documented by its author as a testing SLERP merge of ReML and Huginn v1.2, intended to recreate the original MythoMax with updated components. The model card supplies fp16 files, an Alpaca prompt template, and a detailed multi-stage merge recipe, and declares a CC BY-NC 4.0 license. OpenRouter lists a 6,144-token context and broad sampling plus structured-output controls. Published Open LLM Leaderboard results exist, but they are uneven and are not workload-specific evidence.[1][2]
Strengths
- Author documentation lists the component models and gives a concrete, multi-stage merge workflow.[2]
- OpenRouter reports text-only input and output, a 6,144-token context, structured outputs, and common sampling controls.[1]
- An Alpaca prompt template and fp16 artifacts are documented, giving basic implementation details.[2]
Limitations
- The author calls the model a recreation trial and marks the SLERP merge as testing, so stability and deployment readiness are not established.[2]
- Published leaderboard measurements are uneven, with much lower GSM8K and DROP results than the commonsense-oriented tasks.[2]
- The pack contains only catalog data and a short model card; it lacks dedicated safety testing, hardware requirements, deployment guidance, and validation on real workloads.[1][2]
Where to use it
- Experimental instruction-following or open-ended text generation using Alpaca-style prompts, with suitability checked on target prompts.[1][2]
- Model-merge research, such as comparing this SLERP-merged 13B checkpoint with other checkpoints.[2]
- Text-only prototyping that may benefit from structured outputs or detailed generation controls exposed through OpenRouter.[1]
Sources
- [1] OpenRouter catalog · ReMM SLERP 13BSources checked: Nov 13, 2026
- [2] Model documentation · ReMM SLERP 13BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge
Specifications
- Model ID
- undi95/remm-slerp-l2-13b
- Creator
- undi95
- Added to OpenRouter
- 22.07.2023
- Context length
- 6,144
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.300 / out $0.500
- Knowledge cutoff
- 30.06.2023
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mancer 2fp8 | 6,144 | $0.300 | $0.500 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.