OL

ollama3.1

OllamaGGUF by xzlinuxmodelsUpdated 2024-08-06
Download on Hugging Face
Parameters8B
Context128K
Layers32
Architecturellama
Smallest quant6.6 GB
Quick answer

ollama3.1 needs about 8.2 GB of memory at Q6_K (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 6.6 GB (Q6_K) to 16.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

8‑billion‑parameter Ollama 3.1 model in GGUF format

Ollama 3.1 is an 8‑billion‑parameter llama‑style model. It supports a context length of 131072 tokens and is released under the Apache‑2.0 license. The model is available in two GGUF quantizations.

Good at

  • Large context handling
  • High‑capacity language modeling
  • Apache‑2.0 licensed

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • Only two quantizations available

Best for

  • Chatbots needing long context
  • Research on large‑language‑model behavior
  • Fine‑tuning with open‑source license

Who it’s for. Developers and researchers who need a large, open‑source language model with a long context window. The model is suitable for projects that can accommodate the memory requirements of the available quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K6.6 GB 8.2 GB
Too big Get file →
BF1616.1 GB 17.6 GB
Too big Get file →

For 8‑GB VRAM use the Q6_K quantization (6.6 GB file, ~8.2 GB VRAM at 8 k context). For larger memory budgets use the BF16 quantization (16.07 GB file, ~17.6 GB VRAM at 8 k context).

What GPU do you need for ollama3.1?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.6 GB in use).

Which ollama3.1 quant should you choose?

Q6_K (6.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byxzlinuxmodels
FamilyOllama
Licenseapache-2.0
Downloads (HF)7,918
Last updated2024-08-06

Frequently asked questions about ollama3.1

How much VRAM does ollama3.1 need?

About 8.2 GB at Q6_K with an 8K context window. That is the 6.6 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 ollama3.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ollama3.1 GGUF?

It depends on the quant: Q6_K is 6.6 GB, BF16 is 16.1 GB.

What context length does ollama3.1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download ollama3.1 GGUF?

The files are on Hugging Face in the xzlinuxmodels/ollama3.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ollama3.1 use?

Hugging Face lists the license as apache-2.0. 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 Ollama 3.1 on 8 GB VRAM?

Yes, using the Q6_K quantization which requires about 8.2 GB VRAM at 8 k context.

Does Ollama 3.1 support vision?

No, the model has no vision capabilities.

What license is Ollama 3.1 released under?

It is released under the Apache‑2.0 license.

Similar models

Browse all →

More Ollama models

All Ollama →

Other small models

All small models →