xai-org/grok-1
Grok open release observed · 2026-08-28
Health v2 · maintenance only
25/100
- Activity 0
- Release rhythm 35
- Longevity 64
Flags: no_releases
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 899
- days_rel: n/a
- days_push: 733
- n_releases_24m: 0
Adoption not part of the score
52189 stars · 8541 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
xAI's open release of the Grok-1 open-weights model (314B-parameter Mixture-of-Experts LLM) with JAX example code for loading and running inference. Weights are distributed via torrent or HuggingFace Hub under Apache 2.0.
Use cases
- run grok-1 open weights model locally
- load a 314B mixture-of-experts LLM in JAX
- sample text from grok-1 checkpoint
- experiment with MoE transformer architecture
- quantize a large language model to 8-bit
- self-host an open-source LLM on GPUs
When to choose
- you have multi-GPU hardware with enough memory for a 314B model
- you want to study or fine-tune a large open-weights MoE model
- you need an Apache-2.0 licensed LLM for research
When to avoid
- you lack substantial GPU memory (the model is 314B parameters)
- you need efficient production inference (the MoE implementation is intentionally unoptimized)
- you want a small or lightweight model for consumer hardware
Facets
library · maturity maintenance
llm-inference machine-learning deep-learning large-language-models deep-learning artificial-intelligence python jax mixture-of-experts open-weights grok-1 314b-parameters sentencepiece gpu linux
1 source
- readme: https://github.com/xai-org/grok-1 · fetched 2026-08-28 · 69b897742758
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| xai-org/grok-1 | main | 25 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem