RU

rune 26b a4b v3

RuneGGUF by LivesportUpdated 2026-10-04
Download on Hugging Face
Parameters25.2B
Context—
Layers—
Architecture—
Smallest quant0.1 GB
Quick answer

rune 26b a4b v3 needs about 15.7 GB of memory at IQ3_S (a 13.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 0.1 GB to 26.9 GB (Q8_0).

Rune 26B-A4B v3 – decision model in GGUF format

Rune 26B-A4B v3 is a 26‑billion‑parameter decision model released under the apache‑2.0 license. It is provided in several llama.cpp GGUF quantizations and is designed to return option probabilities from a given state and question. The model contains no vision tower and operates only on text.

Good at

  • Returns probabilities for multiple‑choice questions
  • Runs on llama.cpp with per‑tensor quantization
  • Supports dynamic IQ3_S in production

Limits

  • No vision support – image states are not supported
  • Requires 8‑k context for memory estimates
  • Large memory footprint for higher‑precision quants

Best for

  • Decision‑making pipelines
  • API backends for question answering
  • Production inference on GPUs with 8 GB VRAM

Who it’s for. Engineers building decision‑making services that need a lightweight, quantized model. The model is suitable for developers using llama.cpp and requiring a deterministic probability output for each option.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 0.6 GB
Fits Get file →
IQ3_S13.6 GB 15.7 GB
Too big Get file →
IQ4_XS16.7 GB 19.3 GB
Too big Get file →
Q8_026.9 GB 30.6 GB
Too big Get file →

For 8 GB VRAM, use the IQ3_S quant file (13.6 GB file, 15.7 GB estimated memory at 8 k context). If more VRAM is available, the IQ4_XS file (16.74 GB, 19.3 GB memory) offers higher precision. The Q8_0 quant (26.86 GB, 30.6 GB memory) should be used only on systems with large VRAM and CPU RAM.

What GPU do you need for rune 26b a4b v3?

These figures add the file size, an fp16 KV cache at an 8K context window 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 0.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_S (13.6 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (16.7 GB file, about 19.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 30.6 GB in use).

Which rune 26b a4b v3 quant should you choose?

IQ3_S (13.6 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 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

Parameters25.2B

Source

Quantized byLivesport
FamilyRune
Licenseapache-2.0
Downloads (HF)5,639
Last updated2026-10-04

Frequently asked questions about rune 26b a4b v3

How much VRAM does rune 26b a4b v3 need?

About 15.7 GB at IQ3_S with an 8K context window. That is the 13.6 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 rune 26b a4b v3 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rune 26b a4b v3 GGUF?

It depends on the quant: file is 0.1 GB, IQ3_S is 13.6 GB, IQ4_XS is 16.7 GB, Q8_0 is 26.9 GB.

Where can I download rune 26b a4b v3 GGUF?

The files are on Hugging Face in the Livesport/rune-26b-a4b-v3-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 rune 26b a4b v3 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 the IQ3_S quant on a GPU with 8 GB VRAM?

Yes, the IQ3_S quant requires approximately 15.7 GB of VRAM at 8 k context, which is within the limits of an 8 GB GPU when using efficient batching.

Does this model support image inputs?

No. The GGUF files contain only the language model; image states are not supported.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of rune-26b-a4b-GGUF

Similar models

Browse all →

More from Livesport

All by Livesport →

Other medium models

All medium models →