HE

Heimdallr v0.02 31B

HeimdallrGGUF by Phil2SatUpdated 2026-06-23
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant9.5 GB
Quick answer

Heimdallr v0.02 31B needs about 44.8 GB of memory at IQ3_XXS (a 12.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 9.5 GB (IQ2_XS) to 16.7 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Heimdallr v0.02 31B is a 30.7B-parameter Heimdallr model in GGUF format, quantized by Phil2Sat. Its trained context length is 256K tokens. The repository has 4 quant files, from 9.5 GB (IQ2_XS) to 16.7 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XS9.5 GB 42.2 GB
Too big Get file →
IQ3_XXS12.1 GB 44.8 GB
Too big Get file →
IQ3_XS13.1 GB 45.8 GB
Too big Get file →
IQ4_XS16.7 GB 49.4 GB
Too big Get file →

What GPU do you need for Heimdallr v0.02 31B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is IQ3_XS (13.1 GB file, about 45.8 GB in use).

Which Heimdallr v0.02 31B quant should you choose?

IQ3_XXS (12.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_XS at 9.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byPhil2Sat
FamilyHeimdallr
Downloads (HF)72
Last updated2026-06-23

Frequently asked questions about Heimdallr v0.02 31B

How much VRAM does Heimdallr v0.02 31B need?

About 44.8 GB at IQ3_XXS with an 8K context window. That is the 12.1 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 Heimdallr v0.02 31B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Heimdallr v0.02 31B GGUF?

It depends on the quant: IQ2_XS is 9.5 GB, IQ3_XXS is 12.1 GB, IQ3_XS is 13.1 GB, IQ4_XS is 16.7 GB.

What context length does Heimdallr v0.02 31B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download Heimdallr v0.02 31B GGUF?

The files are on Hugging Face in the Phil2Sat/Heimdallr-v0.02-31B-HB16-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Phil2Sat

All by Phil2Sat →

More Heimdallr models

All Heimdallr →

Other medium models

All medium models →