GR

xai org grok 2

GrokGGUF by bartowskiUpdated 2025-09-17
Download on Hugging Face
Parameters270B
Context128K
Layers64
Architecturegrok
Smallest quant0.1 GB
Quick answer

xai org grok 2 needs about 166.7 GB of memory at Q4_K_M (a 164.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.1 GB to 286.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

xai org grok 2 – 270B parameter Mixture of Experts model

xai org grok 2 is a 270B parameter Mixture of Experts model trained by xAI in 2024. It supports a context length of 131072 tokens and is available in multiple GGUF quantizations. The model is licensed under the Grok 2 Community License Agreement.

Good at

  • Large context reasoning
  • High‑capacity language modeling
  • Mixture of Experts inference

Limits

  • Requires > 40GB VRAM for full precision
  • No vision support
  • License is community‑only

Best for

  • Enterprise chatbot deployment
  • Long‑form content generation
  • Research on Mixture of Experts models

Who it’s for. Developers and researchers needing a large‑scale language model with extensive context. The model is suitable for teams with access to high‑memory GPUs and a need for Mixture of Experts capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 2.7 GB
Fits Get file →
IQ1_M61.4 GB (2 parts) 64.0 GB
Too big Get file →
IQ2_XXS68.5 GB (2 parts) 71.2 GB
Too big Get file →
IQ2_XS77.7 GB (2 parts) 80.4 GB
Too big Get file →
IQ2_S78.7 GB (2 parts) 81.4 GB
Too big Get file →
IQ2_M88.2 GB (3 parts) 90.9 GB
Too big Get file →
Q2_K96.6 GB (3 parts) 99.2 GB
Too big Get file →
Q2_K_L97.6 GB (3 parts) 100.3 GB
Too big Get file →
IQ3_XXS107.0 GB (3 parts) 109.6 GB
Too big Get file →
IQ3_XS111.8 GB (3 parts) 114.5 GB
Too big Get file →
Q3_K_S118.0 GB (3 parts) 120.7 GB
Too big Get file →
IQ3_M123.7 GB (4 parts) 126.4 GB
Too big Get file →
Q3_K_M125.0 GB (4 parts) 127.7 GB
Too big Get file →
Q3_K_L130.2 GB (4 parts) 132.9 GB
Too big Get file →
Q3_K_XL131.2 GB (4 parts) 133.8 GB
Too big Get file →
IQ4_XS144.8 GB (4 parts) 147.4 GB
Too big Get file →
IQ4_NL153.0 GB (4 parts) 155.6 GB
Too big Get file →
Q4_0154.7 GB (4 parts) 157.4 GB
Too big Get file →
Q4_K_S157.5 GB (4 parts) 160.2 GB
Too big Get file →
Q4_K_M164.1 GB (5 parts) 166.7 GB
Too big Get file →
Q4_K_L164.9 GB (5 parts) 167.5 GB
Too big Get file →
Q4_1169.2 GB (5 parts) 171.8 GB
Too big Get file →
Q5_K_S185.9 GB (5 parts) 188.5 GB
Too big Get file →
Q5_K_M191.6 GB (5 parts) 194.2 GB
Too big Get file →
Q6_K221.4 GB (6 parts) 224.0 GB
Too big Get file →
Q8_0286.4 GB (8 parts) 289.0 GB
Too big Get file →

For 8GB VRAM, the smallest quant is unknown (0.09 GB) but memory estimate is 2.7 GB at 8K context, so it fits. For 16GB VRAM, use IQ1_M (61.38 GB file, 64 GB memory). For 24GB VRAM, IQ2_XXS (68.52 GB file, 71.2 GB memory). For 40GB VRAM, Q2_K (96.56 GB file, 99.2 GB memory).

What GPU do you need for xai org grok 2?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 2.7 GB in use).

Which xai org grok 2 quant should you choose?

Q4_K_M is the usual starting point for xai org grok 2: it balances file size and quality well. Here it is a 164.1 GB file.

The Q8_0 file is 286.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegrok
Parameters270B (approximate, mixture of experts)
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

Quantized bybartowski
FamilyGrok
Base modelxai-org/grok-2
Licenseother
Downloads (HF)1,091
Last updated2025-09-17

Frequently asked questions about xai org grok 2

How much VRAM does xai org grok 2 need?

About 166.7 GB at Q4_K_M with an 8K context window. That is the 164.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run xai org grok 2 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of xai org grok 2 GGUF?

It depends on the quant: file is 0.1 GB, IQ1_M is 61.4 GB, IQ2_XXS is 68.5 GB, IQ2_XS is 77.7 GB, IQ2_S is 78.7 GB, IQ2_M is 88.2 GB and 20 more.

What context length does xai org grok 2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download xai org grok 2 GGUF?

The files are on Hugging Face in the bartowski/xai-org_grok-2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does xai org grok 2 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run xai org grok 2 on 8GB VRAM?

The smallest quant is 0.09 GB with an estimated 2.7 GB memory at 8K context, so it can run on 8GB VRAM.

What is the context length of this model?

The model supports 131072 tokens of context.

Does this model support vision tasks?

No, the model has no vision support.

Other GGUFs of grok-2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Grok models

All Grok →

Other large models

All large models →