SI

Sieve 31B v3

SieveGGUF by mradermacherUpdated 2026-10-28
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant11.9 GB
Quick answer

Sieve 31B v3 needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 11.9 GB (Q2_K) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Sieve 31B v3 – a 30.7B Gemma4 decision model

Sieve 31B v3 is a 30.7B parameter Gemma4 model fine‑tuned for decision tasks. It reads a state once, scores options, and outputs calibrated probabilities without generating text. The model is licensed under apache‑2.0.

Good at

  • Decision making
  • Reasoning
  • Tool usage

Limits

  • No text generation
  • No vision support
  • Requires 8k context for memory estimates

Best for

  • Calibrated probability scoring
  • Decision support systems
  • Automated QA

Who it’s for. Developers needing a lightweight decision model that can be integrated into pipelines. The model is ideal for applications that require fast, non‑generative inference and calibrated option scoring.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.9 GB 44.6 GB
Too big Get file →
Q3_K_S13.8 GB 46.5 GB
Too big Get file →
Q3_K_M15.3 GB 48.0 GB
Too big Get file →
Q3_K_L16.6 GB 49.3 GB
Too big Get file →
IQ4_XS16.9 GB 49.6 GB
Too big Get file →
Q4_K_S17.8 GB 50.5 GB
Too big Get file →
Q4_K_M18.7 GB 51.4 GB
Too big Get file →
Q5_K_S21.3 GB 54.0 GB
Too big Get file →
Q5_K_M21.8 GB 54.6 GB
Too big Get file →
Q6_K25.2 GB 57.9 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →

For 8 GB VRAM use Q2_K (11.92 GB, 44.6 GB memory). For 16 GB VRAM use Q4_K_M (18.69 GB, 51.4 GB memory). For 32 GB VRAM use Q8_0 (32.64 GB, 65.3 GB memory). Estimates are approximate.

What GPU do you need for Sieve 31B v3?

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 Q3_K_M (15.3 GB file, about 48.0 GB in use).

Which Sieve 31B v3 quant should you choose?

Q4_K_M is the usual starting point for Sieve 31B v3: it balances file size and quality well. Here it is a 18.7 GB file.

The Q8_0 file is 32.6 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 Q2_K at 11.9 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 bymradermacher
FamilySieve
Licenseapache-2.0
Downloads (HF)811
Last updated2026-10-28

Frequently asked questions about Sieve 31B v3

How much VRAM does Sieve 31B v3 need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Sieve 31B v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sieve 31B v3 GGUF?

It depends on the quant: Q2_K is 11.9 GB, Q3_K_S is 13.8 GB, Q3_K_M is 15.3 GB, Q3_K_L is 16.6 GB, IQ4_XS is 16.9 GB, Q4_K_S is 17.8 GB and 5 more.

What context length does Sieve 31B v3 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 Sieve 31B v3 GGUF?

The files are on Hugging Face in the mradermacher/Sieve-31B-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 Sieve 31B 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 Sieve 31B v3 on 8 GB VRAM?

Use the Q2_K quant, which is 11.92 GB and requires about 44.6 GB of memory at 8k context.

Does the model support image inputs?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Sieve-31B-v3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sieve models

All Sieve →

Other medium models

All medium models →