The story so far
Weights, every dated article, and repo commits on one rail.
10 repo commits since the weights landed
Teal is the weights (2023-08-10), grey ticks are repo commits.
MythoMax-L2-13b
Text in, text out, 4K tokens of context. 4 providers serve it from $0.080 per million input tokens.
Verified 2026-10-25 Rank #408 in LLMs · score 79.2 method v1 Sources 5 Downloads 30d 1.3k · #588 of 619 tracked
Can I use it?OtherCustom license; read the repo LICENSE before commercial hostinglicence file2026-10-24
Do people use it?1.3kdownloads, 30 days#588 of 619 we track · below the median+2 likes, downloads +4% this week410 likesHugging Face2026-10-24
Where to run it
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
Prices for the same weights vary 5×
3 providers with a live price, from $0.080 to $0.40 per million input tokens; the median is $0.35. One dot per provider, cheapest in teal.
Where it's used
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 4 API providers; 18 quantized builds for local use.
- As a service4DeepInfra, Featherless, Mancer 2, Parasail
- On own hardware18quantized builds
- Built on142 fine-tunes · 6 adapters · 6 merges
- In apps80Hugging Face Spaces
Top Spaces running it: AiActivity/AI-Assistant ♥ 21 · NiansuhAI/Main ♥ 10 · PeepDaSlan9/Gryphe-MythoMax-L2-13b ♥ 6 · ChrisNguyenAI/Chat-multi-models ♥ 5
What people built on it
32 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
32 derivatives on the Hub, most of them quantized
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
Use-case evidence
2 use cases
What it is good at 2 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Facts
17 fields
Listed in LLMs
Facts
- Context length is 4,096 tokens (4K). (config.json max_position_embeddings, observed 2026-10-24)
- License: Other (friction: review). Custom license; read the repo LICENSE before commercial hosting. (license file, observed 2026-10-24)
- Created 2023-08-10, last modified 2024-04-21. (HF API, observed 2026-10-24)
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | LlamaForCausalLM |
| Model type | llama |
| Dtype | float16 |
| MoE | no |
| Context length | 4,096 (config.json max_position_embeddings) |
| Languages | en |
| License | Other (other) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · LlamaForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · LlamaForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
All variants
32 variants
Lineage
quantized: 18finetune: 2merge: 6adapter: 6
Top variants (32 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| TheBloke/MythoMax-L2-13B-GGUF | quantized | GGUF | — | — | other | TheBloke | 295 | 1.4M |
| TheBloke/MythoMax-L2-13B-GPTQ | quantized | GPTQ | 13.0B | L | other | TheBloke | 220 | 559.3k |
| Clevyby/Mythomax-L2-13b-Q4_K_M-GGUF | quantized | GGUF | — | — | other | Clevyby | 12 | 77.3k |
| TheBloke/MythoMax-L2-13B-AWQ | quantized | AWQ | 13.0B | L | other | TheBloke | 12 | 40.4k |
| mradermacher/MythoMax-L2-13b-GGUF | quantized | GGUF | — | — | other | mradermacher | 2 | 17.9k |
| mradermacher/MythoMax-L2-13b-i1-GGUF | quantized | GGUF | — | — | other | mradermacher | 5 | 16.6k |
| Andrewwwwww/MythoMax-L2-13B-GGUF | quantized | GGUF | — | — | other | Andrewwwwww | 1 | 8.1k |
| DevQuasar-11/Gryphe.MythoMax-L2-13b-GGUF | quantized | GGUF | — | — | — | DevQuasar-11 | 0 | 6.9k |
| TheBloke/MythoMax-L2-13B-GGML | finetune | — | — | — | llama2 | TheBloke | 83 | 2.6k |
| zihuiliu7737/MythoMax-L2-13B-GGUF | quantized | GGUF | — | — | other | zihuiliu7737 | 3 | 6.5k |
| QuantFactory/Maxtopia-13B-GGUF | merge | GGUF | — | — | — | QuantFactory | 2 | 3k |
| Ragnarock51/MythoMax-L2-13B-GGUF | quantized | GGUF | — | — | other | Ragnarock51 | 1 | 3k |
| Ararath/MythoMax-L2-13B-GGUF | quantized | GGUF | — | — | other | Ararath | 0 | 3k |
| py-sandy/MythoMax-L2-13B-GGUF-FP16 | quantized | GGUF | — | — | other | py-sandy | 1 | 2.8k |
| theNovaAI/Hypernova-experimental-GGUF | quantized | GGUF | — | — | cc-by-nc-sa-4.0 | theNovaAI | 0 | 1.5k |
| backyardai/Psyonic-Cetacean-MythoMax-Ultra-Quality-29B | merge | — | 28.2B | L | — | backyardai | 1 | 485 |
| huanhuamengxue/MythoMax-L2-13b-GGUF | quantized | GGUF | — | — | other | huanhuamengxue | 0 | 419 |
| 4bit/MythoMax-L2-13B-GPTQ | quantized | GPTQ | 13.0B | L | other | 4bit | 0 | 376 |
| youndukn/mythomax-7b-sft-qlora | adapter | — | — | — | other | youndukn | 0 | 242 |
| GusPuffy/sq-MythoMax-L2-13b-w4-s0 | quantized | — | — | — | other | GusPuffy | 0 | 222 |
| youndukn/mythomax-13b-sft-lora | adapter | — | — | — | other | youndukn | 0 | 156 |
| theNovaAI/Hypernova-experimental | finetune | — | 13.0B | L | cc-by-nc-sa-4.0 | theNovaAI | 0 | 151 |
| ClaudioItaly/Maxtopia-13B | merge | — | 13.0B | L | — | ClaudioItaly | 1 | 62 |
| neils1984/SnowyMaxRP-l2-13b | merge | — | 13.0B | L | — | neils1984 | 1 | 39 |
| gotchu/season-8-13bmerge | merge | — | 13.0B | L | — | gotchu | 0 | 81 |
| Guilherme34/Samantha-Mythomax-l2-13b | adapter | — | — | — | — | Guilherme34 | 1 | 30 |
| mergekit-community/mergekit-passthrough-vptgfhk | merge | — | 14.3B | L | — | mergekit-community | 0 | 69 |
| theNovaAI/Hypernova-experimental-GPTQ | quantized | GPTQ | — | — | cc-by-nc-sa-4.0 | theNovaAI | 0 | 67 |
| youndukn/mythomax_lora_adapter | adapter | — | — | — | — | youndukn | 0 | 66 |
| youndukn/zephyr-7b-sft-qlora-8bit-adapter | adapter | -8bit | — | — | — | youndukn | 0 | 50 |
| davidmendez/mythomax-jeffrey | quantized | — | 13.0B | L | other | davidmendez | 0 | 35 |
| luisgarcia29/mi-modelo-tab | adapter | — | — | — | — | luisgarcia29 | 0 | 31 |
Repository changelog
10 commits
Repository changelog 10 commits
| Date | Commit | SHA |
|---|---|---|
| 2024-04-21 | Update README.md | 58e77dd |
| 2023-12-07 | Update README.md | 7dea2ad |
| 2023-09-04 | Upload config.json | c55b8ba |
| 2023-08-11 | Update README.md | faa4ef8 |
| 2023-08-11 | Update README.md | 651aade |
| 2023-08-11 | Update README.md | 4ed8351 |
| 2023-08-11 | Update README.md | 49963c6 |
| 2023-08-10 | Update README.md | 1d22652 |
| 2023-08-10 | Upload 20 files | 319d19b |
| 2023-08-10 | initial commit | 9dfd6ab |
All providers
4 providers · 4 endpoints
Where to run 4 providers · 4 endpoints
Hosted endpoints observed for MythoMax-L2-13b, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.08/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Parasail parasail, openrouter | parasail-mythomax-13b | 4K | fp16 | $0.08 | $0.11 | — | — | — | serverless | 2026-10-24 |
| Mancer 2 openrouter | gryphe/mythomax-l2-13b | 8K | fp8 | $0.35 | $0.60 | — | — | — | live | 2026-10-24 |
| DeepInfra openrouter | gryphe/mythomax-l2-13b | 4K | fp16 | $0.40 | $0.40 | — | — | — | live | 2026-10-24 |
| Featherless hf | Gryphe/MythoMax-L2-13b | — | — | — | — | — | — | — | live | 2026-10-25 |
Similar models
3 models
Similar models
- opt-125m same task (text-generation)
- gpt-j-6b same task (text-generation), permissive license
- DialoGPT-medium same task (text-generation), permissive license
Sources
5 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:39 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:09 UTC · Last verified 2026-10-25
Follow MythoMax-L2-13b
Watch this model
- /feeds/models/Gryphe--MythoMax-L2-13b.xml(RSS 2.0) · every change to MythoMax-L2-13b
- /feeds/families/Gryphe--MythoMax.xml(RSS 2.0) · every change across the MythoMax family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.