QW

dnotitia_Smoothie Qwen3 4B

QwenGGUF by AlcoftUpdated 2025-09-10
Download on Hugging Face
Parameters4B
Context40K
Layers36
Architectureqwen3
Smallest quant1.5 GB
Quick answer

dnotitia_Smoothie Qwen3 4B needs about 4.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 33 quants, from 1.5 GB (Q2_K) to 8.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

4B Qwen3 model optimized for balanced multilingual generation

dnotitia_Smoothie Qwen3 4B is a 4B‑parameter Qwen3 model fine‑tuned with Smoothie Qwen to improve token probability smoothing. It supports up to 40960 context tokens and is released under the apache‑2.0 license.

Good at

  • Reasoning
  • Balanced multilingual output
  • Smooth token probabilities

Limits

  • No vision support
  • Requires 8k context for estimates
  • Large VRAM needed for higher quants

Best for

  • Chatbots needing balanced language
  • Multilingual content generation
  • Fine‑tuned reasoning tasks

Who it’s for. Developers building lightweight multilingual LLMs who need improved token smoothing without large models. Suitable for local deployment with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.5 GB 3.2 GB
Fits Get file →
Q2_K_XS1.5 GB 3.2 GB
Fits Get file →
Q2_K_XXS1.5 GB 3.2 GB
Fits Get file →
Q3_K_S1.7 GB 3.4 GB
Fits Get file →
Q3_K_XS1.7 GB 3.4 GB
Fits Get file →
Q3_K_XXS1.7 GB 3.4 GB
Fits Get file →
Q2_K_L1.8 GB 3.5 GB
Fits Get file →
Q3_K_M1.9 GB 3.6 GB
Fits Get file →
Q3_K_L2.1 GB 3.8 GB
Fits Get file →
Q2_K_XL2.1 GB 3.8 GB
Fits Get file →
Q4_K_S2.3 GB 4.0 GB
Fits Get file →
Q4_K_XS2.3 GB 4.0 GB
Fits Get file →
Q3_K_XL2.3 GB 4.0 GB
Fits Get file →
Q4_K_M2.4 GB 4.1 GB
Fits Get file →
Q4_K_L2.6 GB 4.3 GB
Fits Get file →
Q3_K2.7 GB 4.4 GB
Fits Get file →
Q5_K_S2.8 GB 4.5 GB
Fits Get file →
Q5_K_XS2.8 GB 4.5 GB
Fits Get file →
Q5_K_XXS2.8 GB 4.5 GB
Fits Get file →
Q5_K_M2.8 GB 4.5 GB
Fits Get file →
Q4_K_XL3.0 GB 4.7 GB
Fits Get file →
Q5_K_L3.0 GB 4.7 GB
Fits Get file →
Q6_K3.3 GB 5.0 GB
Fits Get file →
Q6_K_S3.3 GB 5.0 GB
Fits Get file →
Q5_K_XL3.3 GB 5.1 GB
Fits Get file →
Q6_K_L3.4 GB 5.1 GB
Fits Get file →
Q6_K_XL3.8 GB 5.5 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
Q8_K_S4.3 GB 6.0 GB
Fits Get file →
Q8_K_XS4.3 GB 6.0 GB
Fits Get file →
Q8_K_XL4.6 GB 6.4 GB
Fits Get file →
—8.1 GB 9.8 GB
Too big Get file →
F168.1 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S or Q4_K_XS (file size 2.28 GB, ~4 GB memory). For 12 GB VRAM, Q5_K_M or Q5_K_XL (file size 2.84 GB, ~4.5 GB memory). For 16 GB VRAM, Q6_K_XL (file size 3.77 GB, ~5.5 GB memory). Estimates are approximate.

What GPU do you need for dnotitia_Smoothie Qwen3 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_XL (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_K_XL (4.6 GB file, about 6.4 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 dnotitia_Smoothie Qwen3 4B quant should you choose?

Q4_K_M is the usual starting point for dnotitia_Smoothie Qwen3 4B: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.3 GB, about 1.8 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 1.5 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 context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized byAlcoft
FamilyQwen
Licenseapache-2.0
Downloads (HF)3,268
Last updated2025-09-10

Frequently asked questions about dnotitia_Smoothie Qwen3 4B

How much VRAM does dnotitia_Smoothie Qwen3 4B need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 dnotitia_Smoothie Qwen3 4B on an 8 GB GPU?

Yes, with Q8_K_XL: the 4.6 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of dnotitia_Smoothie Qwen3 4B GGUF?

It depends on the quant: Q2_K is 1.5 GB, Q2_K_XS is 1.5 GB, Q2_K_XXS is 1.5 GB, Q3_K_S is 1.7 GB, Q3_K_XS is 1.7 GB, Q3_K_XXS is 1.7 GB and 27 more.

What context length does dnotitia_Smoothie Qwen3 4B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). 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 dnotitia_Smoothie Qwen3 4B GGUF?

The files are on Hugging Face in the Alcoft/dnotitia_Smoothie-Qwen3-4B-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 dnotitia_Smoothie Qwen3 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 this model on 8 GB VRAM?

Yes, using Q4_K_S or Q4_K_XS quantization, which requires about 4 GB of VRAM at 8k context.

Does this model support vision?

No, the model has no vision capabilities.

What license applies?

The model is released under the apache‑2.0 license.

Other GGUFs of Smoothie-Qwen3-4B

Similar models

Browse all →

More from Alcoft

All by Alcoft →

More Qwen models

All Qwen →

Other small models

All small models →