What GPU do I need to run surogate/rune-26b-a4b-GGUF?
25.8B parameters, published in BF16. View on Hugging FaceGated
rune-26b-a4b-GGUF is published by surogate on Hugging Face, with 4,950 downloads and 66 likes to date. It's a Gemma4ForConditionalGeneration model built for text-classification, published natively in BF16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights. Its name carries the GGUF tag.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 48.1 GB | 57.7 GB | A100 | 1 | $1.31/hr |
| cheaper alt. | RTX A5000 | 3 | $0.528/hr | ||
| FP8 (quantized) | 24.0 GB | 28.8 GB | RTX 5000 Ada | 1 | $0.539/hr |
| cheaper alt. | RTX 5060 Ti | 2 | $0.330/hr | ||
| INT4 (quantized) | 12.0 GB | 14.4 GB | RTX A4000 | 1 | $0.137/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run rune-26b-a4b-GGUF at its published (BF16) precision: 1× A100, at $1.31/hr per GPU ($1.31/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
rune-26b-a4b-GGUF: common questions
Can rune-26b-a4b-GGUF run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 57.7 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 80.0 GB A100 at $1.31/hr.
Do I need approval to download rune-26b-a4b-GGUF?
Yes. surogate gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 57.7 GB the model needs once you have them.
What is the least VRAM rune-26b-a4b-GGUF can run in?
14.4 GB, at INT4 (quantized), which fits a 16 GB card, against 57.7 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing rune-26b-a4b-GGUF lower the GPU bill?
Yes. At BF16 the cheapest live fit is one A100 at $1.31/hr. At INT4 (quantized) it drops to one RTX A4000 at $0.137/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Gemma 4 models
- gemma-4-26B-A4B-it (25.8B, BF16)
- GEV-26B-Decide (25.8B, BF16)
- Orion-26B-A4B-v1.1 (25.8B, BF16)
- Orion-26B-A4B-v1 (25.8B, BF16)
- gemma-4-26B-A4B-it-qat-q4_0-unquantized (26.5B, BF16)
Lineage
Based on gemma-4-26B-A4B-it.
Alternatives at this size
Other models for text-classification within about a third of rune-26b-a4b-GGUF's 25.8B parameters, from other model lines.
- AutoTrust-Decider-Pro-Vision-27B-v1.1 (27.4B, BF16)
- JEV-27B (26.9B, BF16)
More on rune-26b-a4b-GGUF
Fits on an 80 GB GPU at BF16: every model that fits in 80 GB.
Fits on a 32 GB GPU at FP8: every model that fits in 32 GB.
Fits on a 16 GB GPU at INT4: every model that fits in 16 GB.
Related reading: A100 pricing and specs, How much VRAM you need for LLMs, and What AI inference is.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat