ReMM SLERP 13B
Undi95 · released Sep 4, 2023 · Undi95/ReMM-SLERP-L2-13B
- Type
- Open weightsCreative Commons Attribution-NonCommercial 4.0
- Params
- 13B
- Context
- 6K
about 5K words of context · download allowed, licence restricts use
Our take
Written Sep 1, 2026ReMM SLERP is a 13-billion-parameter text model released in 2023 under a non-commercial licence. It offers low-cost experimentation for hobbyists and researchers, though no benchmark scores verify its quality and its licence blocks most practical deployment.
Pick this for low-cost experimentation with small downloadable models where non-commercial use is acceptable, or budget text-generation tasks that stay inside the licence. Skip it if you need commercial use, measured quality data, or support for images, audio or video.
The case for it
- Lowest input price among its three tracked hosts.
- Fastest measured throughput among hosts with disclosed speed, at 46 tokens per second.
The case against it
- No measured quality scores — chat, reasoning, coding and other capabilities are all unverified.
- Non-commercial licence prohibits most product integration and many research applications.
- Text-only with a 6,144-token request limit, narrow by current standards.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 11.5 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 19.5 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU) · 16 GB
Borderline fit on an estimated size. It leaves 0.7 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.35 in / $0.65 out
- Context served
- 6K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.35 / $0.65checked 4 hours ago | 6K | not measured | Unknown | Unknown | Unknown |
| NextBitbf16Through OpenRouter | $0.45 / $0.65checked 4 hours ago | 6K4K max reply | 22 tok/s | No | No | Confirmed |
| Mancer 2fp8Through OpenRouter | $0.35 / $0.65checked 4 hours ago | 6K6K max reply | 54 tok/s | No | No | Confirmed |
Across the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| NextBitbf16Through OpenRouter | ✗ | ✓ | ✓ |
| Mancer 2fp8Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 3 listings say yes, 3 say no. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
When we formed this view
Recent changes
What moved
input −22% ($0.45 → $0.35 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCreative Commons Attribution-NonCommercial 4.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Creative Commons Attribution-NonCommercial 4.0
Weights are downloadable but commercial use is prohibited. Research and personal use only.
Identifiers
- Hugging Face
- Undi95/ReMM-SLERP-L2-13B
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- undi95-remm-slerp-13b