Skip to content
ModelListedExternal
Download

Qwen3 4B I1 GGUF

static quants are available at

Sourcehuggingface.co/mradermacher/Qwen3-4B-i1-GGUF/tree/main
KindOtherBase modelQwen/Qwen3-4BVersionmain

Model source

Kind
Other
File size
1,006 MB–3.08 GB
Base model
Qwen/Qwen3-4B
Version
vmain
Updated
Sep 29, 2026
Downloads
2K
Source
Hugging Face

Source description

About

weighted/imatrix quants of https://huggingface.co/Qwen/Qwen3-4B

static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

LinkTypeSize/GBNotes
GGUFi1-IQ1_S1.2for the desperate
GGUFi1-IQ1_M1.2mostly desperate
GGUFi1-IQ2_XXS1.3
GGUFi1-IQ2_XS1.5
GGUFi1-IQ2_S1.5
GGUFi1-IQ2_M1.6
GGUFi1-Q2_K_S1.7very low quality
GGUFi1-Q2_K1.8IQ3_XXS probably better
GGUFi1-IQ3_XXS1.8lower quality
GGUFi1-IQ3_XS1.9
GGUFi1-Q3_K_S2.0IQ3_XS probably better
GGUFi1-IQ3_S2.0beats Q3_K*
GGUFi1-IQ3_M2.1
GGUFi1-Q3_K_M2.2IQ3_S probably better
GGUFi1-Q3_K_L2.3IQ3_M probably better
GGUFi1-IQ4_XS2.4
GGUFi1-Q4_02.5fast, low quality
GGUFi1-IQ4_NL2.5prefer IQ4_XS
GGUFi1-Q4_K_S2.5optimal size/speed/quality
GGUFi1-Q4_K_M2.6fast, recommended
GGUFi1-Q4_12.7
GGUFi1-Q5_K_S2.9
GGUFi1-Q5_K_M3.0
GGUFi1-Q6_K3.4practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Sources

1 source
Hugging FacePrimaryVersion main
huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/tree/main

Verified Sep 29

Model artifacts

24 artifacts

Qwen3-4B.i1-IQ1_M.gguf

gguf · 1.05 GB · SHA-256 6bb306b797e1…703e · Hugging Face

Download

Qwen3-4B.i1-IQ1_S.gguf

gguf · 1,006 MB · SHA-256 2923545370da…4859 · Hugging Face

Download

Qwen3-4B.i1-IQ2_M.gguf

gguf · 1.41 GB · SHA-256 322be0eab69c…f491 · Hugging Face

Download

Qwen3-4B.i1-IQ2_S.gguf

gguf · 1.32 GB · SHA-256 e96f1a3d9d8c…6903 · Hugging Face

Download

Qwen3-4B.i1-IQ2_XS.gguf

gguf · 1.26 GB · SHA-256 26a1e8b29ed6…48f9 · Hugging Face

Download

Qwen3-4B.i1-IQ2_XXS.gguf

gguf · 1.16 GB · SHA-256 a9082caac764…4b8f · Hugging Face

Download

Qwen3-4B.i1-IQ3_M.gguf

gguf · 1.83 GB · SHA-256 7eecb7725ffa…0827 · Hugging Face

Download

Qwen3-4B.i1-IQ3_S.gguf

gguf · 1.77 GB · SHA-256 0f42189d158d…a824 · Hugging Face

Download

Qwen3-4B.i1-IQ3_XS.gguf

gguf · 1.69 GB · SHA-256 5dd23e33ad7b…42c3 · Hugging Face

Download

Qwen3-4B.i1-IQ3_XXS.gguf

gguf · 1.56 GB · SHA-256 c5564edf744d…30d8 · Hugging Face

Download

Qwen3-4B.i1-IQ4_NL.gguf

gguf · 2.22 GB · SHA-256 7bece240517a…c258 · Hugging Face

Download

Qwen3-4B.i1-IQ4_XS.gguf

gguf · 2.11 GB · SHA-256 0357e192ca5c…4510 · Hugging Face

Download

Qwen3-4B.i1-Q2_K_S.gguf

gguf · 1.46 GB · SHA-256 9d7b1f989e68…f5be · Hugging Face

Download

Qwen3-4B.i1-Q2_K.gguf

gguf · 1.55 GB · SHA-256 4ad818ab7f76…4b71 · Hugging Face

Download

Qwen3-4B.i1-Q3_K_L.gguf

gguf · 2.09 GB · SHA-256 8f57b32e2065…2d12 · Hugging Face

Download

Qwen3-4B.i1-Q3_K_M.gguf

gguf · 1.93 GB · SHA-256 956f869371ec…2af6 · Hugging Face

Download

Qwen3-4B.i1-Q3_K_S.gguf

gguf · 1.76 GB · SHA-256 d0e715f5f02d…a85c · Hugging Face

Download

Qwen3-4B.i1-Q4_0.gguf

gguf · 2.21 GB · SHA-256 1e13969926ba…3485 · Hugging Face

Download

Qwen3-4B.i1-Q4_1.gguf

gguf · 2.42 GB · SHA-256 886650793eb8…6444 · Hugging Face

Download

Qwen3-4B.i1-Q4_K_M.gguf

gguf · 2.33 GB · SHA-256 fa9513ef8b6d…8012 · Hugging Face

Download

Qwen3-4B.i1-Q4_K_S.gguf

gguf · 2.22 GB · SHA-256 5a71cfa4b3b7…f0b4 · Hugging Face

Download

Qwen3-4B.i1-Q5_K_M.gguf

gguf · 2.69 GB · SHA-256 882d799780c9…91bb · Hugging Face

Download

Qwen3-4B.i1-Q5_K_S.gguf

gguf · 2.63 GB · SHA-256 5c1e0d60d999…3dc0 · Hugging Face

Download

Qwen3-4B.i1-Q6_K.gguf

gguf · 3.08 GB · SHA-256 4436d9c7f0f0…ed78 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 29huggingface.co/mradermacher/Qwen3-4B-i1-GGUF

--- base_model: Qwen/Qwen3-4B language: - en library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Qwen/Qwen3-4B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-i1-GGUF/resolve/main/Qwen3-4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | | [GGUF...

NoteSep 29huggingface.co/mradermacher/Qwen3-4B-i1-GGUF

Source context: 2002 downloads · 5 likes · Library transformers · Repo mradermacher/Qwen3-4B-i1-GGUF