PO

Polaris 4B Preview

PolarisGGUF by dzur658Updated 2026-09-30
Download on Hugging Face
Parameters4B
Context128K
Layers36
Architectureqwen3
Smallest quant1.1 GB
Quick answer

Polaris 4B Preview needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.1 GB (IQ1_S) to 8.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Polaris 4B Preview – a 4B Qwen3 model fine‑tuned with the Polaris post‑training recipe

Polaris 4B Preview is a 4B‑parameter Qwen3 model refined with the Polaris post‑training method. It supports a 131072‑token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Reasoning tasks
  • Long‑form generation
  • Fine‑tuning on custom data

Limits

  • No vision support
  • Requires 8K context for memory estimates
  • License is Apache‑2.0

Best for

  • Chatbots needing long context
  • Academic research on reasoning models
  • Edge deployment with limited VRAM

Who it’s for. Developers and researchers who need a lightweight, reasoning‑capable LLM that can run on consumer GPUs. The model is suitable for those who prefer open‑source tools like llama.cpp and Ollama.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.1 GB 2.8 GB
Fits Get file →
IQ2_XXS1.2 GB 3.0 GB
Fits Get file →
IQ2_XS1.4 GB 3.1 GB
Fits Get file →
IQ2_S1.4 GB 3.1 GB
Fits Get file →
Q2_K_S1.6 GB 3.3 GB
Fits Get file →
Q2_K1.7 GB 3.4 GB
Fits Get file →
IQ3_XXS1.7 GB 3.4 GB
Fits Get file →
Q3_K_S1.9 GB 3.6 GB
Fits Get file →
IQ3_S1.9 GB 3.6 GB
Fits Get file →
Q3_K_M2.1 GB 3.8 GB
Fits Get file →
Q3_K_L2.2 GB 3.9 GB
Fits Get file →
IQ4_XS2.3 GB 4.0 GB
Fits Get file →
Q4_02.4 GB 4.1 GB
Fits Get file →
IQ4_NL2.4 GB 4.1 GB
Fits Get file →
Q4_K_S2.4 GB 4.1 GB
Fits Get file →
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q4_12.6 GB 4.3 GB
Fits Get file →
Q5_K_S2.8 GB 4.5 GB
Fits Get file →
Q5_02.8 GB 4.5 GB
Fits Get file →
Q5_K_M2.9 GB 4.6 GB
Fits Get file →
Q5_13.1 GB 4.8 GB
Fits Get file →
Q6_K3.3 GB 5.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
—8.1 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (1.25 GB) or IQ2_XS (1.35 GB). For 12 GB VRAM, IQ4_XS (2.27 GB) or Q4_0 (2.38 GB) are good choices. Larger VRAM allows Q4_K_M (2.5 GB) or Q5_K_S (2.82 GB) for higher quality.

What GPU do you need for Polaris 4B Preview?

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 IQ4_XS (2.3 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (8.1 GB file, about 9.8 GB in use).

Which Polaris 4B Preview quant should you choose?

Q4_K_M is the usual starting point for Polaris 4B Preview: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 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 IQ1_S at 1.1 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

Architectureqwen3
Parameters4B
Layers36
Trained context131,072 tokens
KV cache (fp16)144 KB per token

Source

Quantized bydzur658
FamilyPolaris
Licenseapache-2.0
Downloads (HF)507
Last updated2026-09-30

Frequently asked questions about Polaris 4B Preview

How much VRAM does Polaris 4B Preview need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Polaris 4B Preview on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Polaris 4B Preview GGUF?

It depends on the quant: IQ1_S is 1.1 GB, IQ2_XXS is 1.2 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.4 GB, Q2_K_S is 1.6 GB, Q2_K is 1.7 GB and 18 more.

What context length does Polaris 4B Preview support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Polaris 4B Preview GGUF?

The files are on Hugging Face in the dzur658/Polaris-4B-Preview-IQ-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 Polaris 4B Preview 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 Polaris 4B Preview on 8 GB VRAM?

Yes, use a quantization like IQ2_XXS or IQ2_XS, which are under 3 GB memory at 8K context.

Does the model support image input?

No, Polaris 4B Preview does not have vision capabilities.

What is the maximum context length?

The model was trained with a 131072‑token context window.

Other GGUFs of Polaris-4B-Preview

Similar models

Browse all →

More from dzur658

All by dzur658 →

More Polaris models

All Polaris →

Other small models

All small models →