Skip to content
ModelListedExternal
Download

TRivia 3B GGUF

For a convenient overview and download list, visit our model page for this model.

Sourcehuggingface.co/mradermacher/TRivia-3B-GGUF/tree/65cbb581c3588d478ec384d4a861ff51b14b256f
KindOtherBase modelopendatalab/TRivia-3BVersionRevision 65cbb58

Model source

Kind
Other
File size
808 MB–6.33 GB
Base model
opendatalab/TRivia-3B
Version
vRevision 65cbb58
Updated
Sep 17, 2026
Downloads
408
Tasks
Captioning
Source
Hugging Face

Source description

About

static quants of https://huggingface.co/opendatalab/TRivia-3B

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/TRivia-3B-i1-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
GGUFmmproj-Q8_00.9multi-modal supplement
GGUFmmproj-f161.4multi-modal supplement
GGUFQ2_K1.5
GGUFQ3_K_S1.7
GGUFQ3_K_M1.8lower quality
GGUFQ3_K_L1.9
GGUFIQ4_XS2.0
GGUFQ4_K_S2.1fast, recommended
GGUFQ4_K_M2.2fast, recommended
GGUFQ5_K_S2.5
GGUFQ5_K_M2.5
GGUFQ6_K2.9very good quality
GGUFQ8_03.7fast, best quality
GGUFf166.916 bpw, overkill

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.

Sources

1 source
Hugging FacePrimaryVersion 65cbb581c3588d478ec384d4a861ff51b14b256f
huggingface.co/mradermacher/TRivia-3B-GGUF/tree/65cbb581c3588d478ec384d4a861ff51b14b256f

Verified Sep 17

Model artifacts

14 artifacts

TRivia-3B.f16.gguf

gguf · 6.33 GB · SHA-256 839903b5d1ed…00de · Hugging Face

Download

TRivia-3B.IQ4_XS.gguf

gguf · 1.79 GB · SHA-256 e81d1c194095…7097 · Hugging Face

Download

TRivia-3B.mmproj-f16.gguf

gguf · 1.25 GB · SHA-256 a760961f57b1…4827 · Hugging Face

Download

TRivia-3B.mmproj-Q8_0.gguf

gguf · 808 MB · SHA-256 dcacc92cdc4c…d472 · Hugging Face

Download

TRivia-3B.Q2_K.gguf

gguf · 1.28 GB · SHA-256 46f17c8e69e0…06ab · Hugging Face

Download

TRivia-3B.Q3_K_L.gguf

gguf · 1.71 GB · SHA-256 4ace065676e0…c711 · Hugging Face

Download

TRivia-3B.Q3_K_M.gguf

gguf · 1.61 GB · SHA-256 d67f368e11b8…9aa7 · Hugging Face

Download

TRivia-3B.Q3_K_S.gguf

gguf · 1.48 GB · SHA-256 93f343da6d93…ef54 · Hugging Face

Download

TRivia-3B.Q4_K_M.gguf

gguf · 1.96 GB · SHA-256 899400f02955…01be · Hugging Face

Download

TRivia-3B.Q4_K_S.gguf

gguf · 1.87 GB · SHA-256 b7978da48f63…9852 · Hugging Face

Download

TRivia-3B.Q5_K_M.gguf

gguf · 2.27 GB · SHA-256 28bfd2a4fdc8…259b · Hugging Face

Download

TRivia-3B.Q5_K_S.gguf

gguf · 2.22 GB · SHA-256 7bb12ff9260a…7aea · Hugging Face

Download

TRivia-3B.Q6_K.gguf

gguf · 2.60 GB · SHA-256 97c563ab6e8f…8936 · Hugging Face

Download

TRivia-3B.Q8_0.gguf

gguf · 3.37 GB · SHA-256 895dd3389f36…1643 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 17huggingface.co/mradermacher/TRivia-3B-GGUF

--- base_model: opendatalab/TRivia-3B language: - en - zh - multilingual library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - table recognition - image-to-text - table --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/opendatalab/TRivia-3B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TRivia-3B-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/TRivia-3B-i1-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/TRivia-3B-GGUF/resolve/main/TRivia-3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.Q2_K.gguf) | Q2_K | 1.5 | | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.Q3_K_S.gguf) | Q3_K_S | 1.7 | | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.IQ4_XS.gguf) | IQ4_XS | 2.0 | | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/TRivia-3B-GGUF/resolve/main/TRivia-3B.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | | [GGU...

NoteSep 17huggingface.co/mradermacher/TRivia-3B-GGUF

Source context: 408 downloads · 0 likes · Pipeline image-to-text · Library transformers · Repo mradermacher/TRivia-3B-GGUF