OSAIM
Open Source AI Models

Grok 2

xAI's second open-weights release, Apache 2.0. ~300B mixture-of-experts. xAI's pattern of open-sourcing the previous frontier when a new one ships continues from Grok 1. Competitive with GPT-4-class chat quality at release; today useful mainly as a research artefact given the compute needed to run it.

Parameters
300B
Context length
131K
Modality
text
Released
2025-03-17

Memory & hardware

VRAM (fp16)
600 GB
VRAM (Q4)
180 GB
Recommended
8× H100 80GB at fp8
Quantizations
fp16, fp8

License: Apache 2.0

SPDX
Apache-2.0
Commercial use
Yes
Modification
Yes
Redistribution
Yes

Benchmarks

No verified benchmark scores yet for this model.

Hosted inference pricing

No hosted pricing listed — this model is currently self-host-only on this site.

Run it yourself

Drop-in commands for the three most common open-source inference paths. The Ollama tag is a best-effort match against the registry; verify the size variant before pulling.

Run Grok 2 locally
No official Ollama registry tag for this model — use transformers or vLLM below.
vLLM (production)
vllm serve xai-org/grok-2
High-throughput hosted inference; one command to expose an OpenAI-compatible HTTP server.
Transformers (Python)
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xai-org/grok-2")
model = AutoModelForCausalLM.from_pretrained(
    "xai-org/grok-2", device_map="auto", torch_dtype="auto"
)
Direct PyTorch usage. Pin a torch / cuda version that matches your GPU.
Hugging Face ID: xai-org/grok-2

Related models

Same family or similar size — useful when shopping around.

Grok 1
314B

xAI's first open-weights release: a 314B-parameter mixture-of-experts model. Apache 2.0 licensed. Largely a research artefact at this size — most users will run smaller models for production — but useful as a permissively-licensed reference for MoE research.

Context
8K
License
apache-2-0
VRAM Q4
188.4 GB
Nemotron-4 340B Instruct
340B

NVIDIA's reward-modelling research vehicle. Trained primarily to be a synthetic-data-generation specialist rather than a chat-first model. Useful for teams building instruction-tuning datasets at scale.

Context
4K
License
llama-3
VRAM Q4
204 GB
DeepSeek Coder V2
236B

Coding-focused MoE model with 21B active parameters out of 236B total. Supports 338 programming languages with strong performance across mainstream stacks (Python, TypeScript, Go, Rust, Java, C++) and competent results on niche languages where most open models falter. The DeepSeek licence applies — commercial use permitted with some application restrictions.

Context
128K
License
deepseek
VRAM Q4
141.6 GB
Qwen 3 235B (A22B)
235B

The flagship Qwen 3 release: a 235B-total MoE with 22B active parameters per token. Competitive with DeepSeek V3 and Llama 4 Maverick on reasoning benchmarks while being smaller total. Apache 2.0 — one of the most permissively licenced frontier-class models.

Context
128K
License
apache-2-0
VRAM Q4
141 GB
Jamba 1.5 Large
398B

Hybrid Mamba-Transformer-MoE model with native 256K context (effective beyond 140K). 94B active parameters out of 398B total. The state-space-model layers give it linear-time scaling with sequence length, making it interesting for very long contexts. Licensed under AI21's open model licence, which permits most commercial use.

Context
256K
License
jamba-open
VRAM Q4
238.8 GB
Llama 3.1 405B Instruct
405B

Meta's July 2024 flagship — the first open-weights model at 405B parameters. Trained on 15T tokens with 128K context. Rivals GPT-4o on many academic benchmarks and set the ceiling for open-weights quality for most of 2024. Running it self-hosted requires serious hardware (8× H100 at fp8 or multi-node at fp16); most users will run it via a hosted provider (Together, Groq, Fireworks). Llama 3.3 70B closed most of the practical gap at a fraction of the cost, so 405B is now most useful when 70B specifically hits its ceiling.

Context
128K
License
llama-3
VRAM Q4
243 GB