Model reference · open weights

llama

Available as managed deployment LLMs JackFram · community Text gen 2 variants 109k dl/mo

llama is an open-weight language model from JackFram. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byJackFram
TypeLanguage models
TaskText gen
Context2k tokens
Runs withtransformers
Released2023-07-19
Popularity109k downloads / month
LicenceOpen weights

About

What llama is

Model description

This is a LLaMA-like model with only 68M parameters trained on Wikipedia and part of the C4-en and C4-realnewslike datasets.

No evaluation has been conducted yet, so use it with care.

Read the full model card

The model is mainly developed as a base Small Speculative Model in the SpecInfer paper.

Evaluations (contributed by Akshit, huge thanks!)

CategoryBenchmarkMetricScore / ValueStatus
Linguistics & GrammarBLiMPAccuracy70.57%Success
Commonsense & ReasoningPIQANormalized Accuracy59.25%Success
BoolQAccuracy57.71%Success
COPAAccuracy53.00%Success
WinoGrandeAccuracy50.59%Success
HellaSwagNormalized Accuracy29.04%Success
RACEAccuracy25.36%Success
CommonsenseQAAccuracy19.82%Success
Academic & KnowledgeSciQNormalized Accuracy57.80%Success
ARC-EasyNormalized Accuracy35.98%Success
OpenBookQANormalized Accuracy25.60%Success
MMLUAccuracy22.96%Success
ARC-ChallengeNormalized Accuracy22.87%Success
Language ModelingTriviaQAAccuracyTriviaQA StandardSuccess
LAMBADAAccuracy13.24%Success
C4-PerplexityWord Perplexity205.79Success
WikiText-2Word Perplexity306.79Success

Notes on Failed Tasks: The Arithmetic and SocialIQA benchmarks failed during execution due to runtime pipeline incompatibilities, yielding no score. Total evaluation runtime was 44.74 minutes.

Citation

To cite the model, please use

@misc{miao2023specinfer,
      title={SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification},
      author={Xupeng Miao and Gabriele Oliaro and Zhihao Zhang and Xinhao Cheng and Zeyu Wang and Rae Ying Yee Wong and Zhuoming Chen and Daiyaan Arfeen and Reyna Abhyankar and Zhihao Jia},
      year={2023},
      eprint={2305.09781},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys jackfram-llama for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (jackfram-llama below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"jackfram-llama","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms