MythoMax 13B
Gryphe · released Aug 10, 2023 · Gryphe/MythoMax-L2-13b
- Type
- Open weightsCustom licence
- Params
- 13B
- Context
- 8K
about 6K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026MythoMax is a 13-billion-parameter text model released in 2023 by Gryphe, available as a download under a custom licence. It is positioned as a budget inference option with several providers offering low rates, though no benchmark scores are available to verify its quality.
Pick this when your only priority is the cheapest possible text generation and you can accept unverified quality. Use it for short-context tasks within 8,192 tokens where cost matters more than measured capability. Skip it if you need a permissive licence, proven benchmark performance, or a larger context window.
The case for it
- Very low entry price for text inference: the cheapest tier is several times cheaper than the most expensive tracked offer.
- Multiple provider options at the budget tier, with two hosts at the lowest rate and one only slightly above.
The case against it
- No verified benchmark performance — zero scores in our data, so quality claims are unsupported.
- Narrow context window for its parameter class, with no larger variant disclosed.
- Custom licence, not a standard permissive one; terms are unspecified in our data, limiting commercial flexibility.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up MythoMax 13B — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 7 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.060 in / $0.060 out
- Context served
- 8K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.060 / $0.060 | 8K | not measured | Unknown | Unknown | Unknown |
| NextBitint4 | $0.060 / $0.060 | 4K | 44 tok/s | No | No | Confirmed |
| Novita AI | $0.090 / $0.090 | 4K | not measured | Unknown | Unknown | Unknown |
| Parasailfp16 | $0.080 / $0.11 | 4K | 58 tok/s | No | No | Confirmed |
| DeepInfrafp16 | $0.40 / $0.40 | 4K | 49 tok/s | No | No | Confirmed |
| DeepInfrafp16 | $0.40 / $0.40 | 4K | not measured | Unknown | Unknown | Unknown |
| Mancer 2fp8 | $0.45 / $0.65 | 8K | 57 tok/s | No | No | Confirmed |
Novita AI
DeepInfraAcross the 7 listings we hold: 4 say they do not train on prompts, 0 say they do and 3 do not say. 4 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| NextBitint4 | ✗ | ✓ | ✓ |
| Novita AI | |||
| Parasailfp16 | ✗ | ✗ | ✓ |
| DeepInfrafp16 | ✗ | ✓ | ✗ |
| DeepInfrafp16 | |||
| Mancer 2fp8 | ✗ | ✓ | ✓ |
Tool calling: 0 of 7 listings say yes, 5 say no, 2 publish no parameter list. JSON output: 4 of 7 listings say yes, 1 says no, 2 publish no parameter list. Strict schema: 4 of 7 listings say yes, 1 says no, 2 publish no parameter list.
When we formed this view
Dates behind this page
Prices last checked 6h ago
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 board we watch has turned up a score, so we hold no quality figures at all.
- 2 of 7 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 3 of 7 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsCustom licence, 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
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- Gryphe/MythoMax-L2-13b
- Architecture
- Dense
- Modality record
- text->text
- Catalogue slug
- gryphe-mythomax-13b