SO

SoulX-Podcast-1.7B

SoulxGGUF by MungertUpdated 2025-10-31
Download on Hugging Face
Parameters2.06B
Context40K
Layers28
Architectureqwen3
Smallest quant0.0 GB
Quick answer

SoulX-Podcast-1.7B needs about 3.0 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.0 GB to 4.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

SoulX-Podcast-1.7B is a 2.06B-parameter Soulx model in GGUF format, quantized by Mungert. Its trained context length is 40K tokens. The repository has 19 quant files, from 0.0 GB to 4.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
IQ3_XXS1.1 GB 2.5 GB
Fits Get file →
IQ3_XS1.1 GB 2.6 GB
Fits Get file →
Q3_K_S1.1 GB 2.6 GB
Fits Get file →
IQ4_NL1.2 GB 2.6 GB
Fits Get file →
IQ3_M1.2 GB 2.6 GB
Fits Get file →
Q3_K_M1.2 GB 2.7 GB
Fits Get file →
IQ4_XS1.3 GB 2.7 GB
Fits Get file →
Q4_11.3 GB 2.8 GB
Fits Get file →
Q4_K_S1.3 GB 2.8 GB
Fits Get file →
Q4_01.5 GB 2.9 GB
Fits Get file →
Q4_K_M1.5 GB 3.0 GB
Fits Get file →
Q5_01.7 GB 3.1 GB
Fits Get file →
Q5_K_M1.7 GB 3.1 GB
Fits Get file →
Q5_11.8 GB 3.2 GB
Fits Get file →
Q6_K_M1.9 GB 3.3 GB
Fits Get file →
Q8_02.2 GB 3.6 GB
Fits Get file →
F163.3 GB 4.7 GB
Fits Get file →
BF164.1 GB 5.6 GB
Fits Get file →

What GPU do you need for SoulX-Podcast-1.7B?

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 Q8_0 (2.2 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (4.1 GB file, about 5.6 GB in use).

Which SoulX-Podcast-1.7B quant should you choose?

Q4_K_M is the usual starting point for SoulX-Podcast-1.7B: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 2.2 GB, about 1.4 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 the first one in the table at 0.0 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

Architectureqwen3
Parameters2.06B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized byMungert
FamilySoulx
Licenseapache-2.0
Downloads (HF)272
Last updated2025-10-31

Frequently asked questions about SoulX-Podcast-1.7B

How much VRAM does SoulX-Podcast-1.7B need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 1.5 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 SoulX-Podcast-1.7B on an 8 GB GPU?

Yes, with BF16: the 4.1 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SoulX-Podcast-1.7B GGUF?

It depends on the quant: file is 0.0 GB, IQ3_XXS is 1.1 GB, IQ3_XS is 1.1 GB, Q3_K_S is 1.1 GB, IQ4_NL is 1.2 GB, IQ3_M is 1.2 GB and 13 more.

What context length does SoulX-Podcast-1.7B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download SoulX-Podcast-1.7B GGUF?

The files are on Hugging Face in the Mungert/SoulX-Podcast-1.7B-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 SoulX-Podcast-1.7B 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.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Soulx models

All Soulx →

Other tiny models

All tiny models →