SO

Sonda 1.0 4B

SondaGGUF by mradermacherUpdated 2026-10-03
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant1.9 GB
Quick answer

Sonda 1.0 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.9 GB (Q2_K) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Sonda 1.0 4B – a decision‑making model for Polish and English

Sonda 1.0 4B is a 4.21B‑parameter decision model built on the qwen35 architecture. It predicts calibrated probabilities for yes/no, choice, and score questions without generating text. The model is served via sonda-server or vLLM and requires an NVIDIA GPU with CUDA.

Good at

  • Calibrated probability prediction
  • Decision‑making tasks
  • No text generation

Limits

  • No vision support
  • Requires CUDA GPU
  • Only Polish and English

Best for

  • Automated decision support
  • Risk assessment tools
  • Score‑based evaluations

Who it’s for. Developers building decision‑making services that need reliable probability estimates. Researchers testing calibrated models on Polish and English datasets.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 3.5 GB
Fits Get file →
Q3_K_S2.1 GB 3.6 GB
Fits Get file →
Q3_K_M2.3 GB 3.8 GB
Fits Get file →
Q3_K_L2.4 GB 4.0 GB
Fits Get file →
IQ4_XS2.5 GB 4.1 GB
Fits Get file →
Q4_K_S2.6 GB 4.1 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_S3.0 GB 4.6 GB
Fits Get file →
Q5_K_M3.1 GB 4.6 GB
Fits Get file →
Q6_K3.5 GB 5.0 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
F168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (2.56 GB, ~4.1 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (3.07 GB, ~4.6 GB memory) offers better quality. Higher‑precision quants like F16 (8.42 GB) need at least 16 GB VRAM.

What GPU do you need for Sonda 1.0 4B?

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: the best quant that fits is Q3_K_L (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.4 GB file, about 10.0 GB in use).

Which Sonda 1.0 4B quant should you choose?

Q4_K_M is the usual starting point for Sonda 1.0 4B: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.5 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 1.9 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

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilySonda
Licenseapache-2.0
Downloads (HF)234
Last updated2026-10-03

Frequently asked questions about Sonda 1.0 4B

How much VRAM does Sonda 1.0 4B need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Sonda 1.0 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sonda 1.0 4B GGUF?

It depends on the quant: Q2_K is 1.9 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, IQ4_XS is 2.5 GB, Q4_K_S is 2.6 GB and 6 more.

What context length does Sonda 1.0 4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Sonda 1.0 4B GGUF?

The files are on Hugging Face in the mradermacher/sonda-1.0-4B-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 Sonda 1.0 4B 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 Sonda 1.0 4B on 8 GB VRAM?

Yes, the Q4_K_S quant is 2.56 GB and requires about 4.1 GB of VRAM at 8 k context, fitting within 8 GB.

Does the model support other languages?

No, it was trained only on Polish and English; other languages are unsupported.

Is the model chat‑capable?

No, it does not generate text; it returns probabilities for decision questions.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sonda models

All Sonda →

Other small models

All small models →