Lite GGUF models

92 GGUF models in the Lite family, quantized by 39 uploaders. Sizes run from 64M to 22.2B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
LI
T lite it 2.1
Lite · t-tech
Params8.2B
Context40K
Q4_K_M5.0 GB
GGUF
LI
vllm-d3-lite
Lite · ggml-org
Params1.01B
Context256K
Smallest1.1 GB
Vision
LI
T Lite It 1.0
Lite · aovchinnikov
Params7.6B
Context32K
Q4_K_M4.7 GB
GGUF
LI
Lite Oute 1 300M Instruct
Lite · mradermacher
Params300M
Context4K
Q4_K_M0.2 GB
GGUF
LI
ozone ai 0x lite
Lite · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
LI
sd3.5 lite
Lite · calcuis
Params2.47B
Context—
Q4_K_M1.8 GB
GGUF
LI
T Lite Instruct 0.1
Lite · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
LI
OmniLing V1 8b experimental
Lite · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LI
T lite instruct 0.1
Lite · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LI
Lite Oute 1 300M
Lite · mradermacher
Params300M
Context4K
Q4_K_M0.2 GB
GGUF
LI
voxprint t lite it 2.1
Lite · Mitroshenkov87
Params8.19B
Context40K
Smallest0.0 GB
GGUF
LI
T lite 0.1
Lite · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LI
ozone research 0x lite
Lite · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
LI
Lite-Oute-1-300M-Instruct
Lite · OuteAI
Params300M
Context4K
Q4_K_M0.2 GB
GGUF
LI
ozone research 2x lite
Lite · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
LI
T Lite Instruct 0.1
Lite · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LI
T lite 0.1
Lite · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LI
0x lite i1
Lite · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
LI
T Lite It 1.0
Lite · mradermacher
Params7.61B
Context32K
Q4_K_M4.7 GB
GGUF
LI
Lite Cydonia 22B v1.1 50 50 i1
Lite · mradermacher
Params22.2B
Context32K
Q4_K_M13.3 GB
Tool use
LI
T Lite It 1.0
Lite · mradermacher
Params7.61B
Context32K
Q4_K_M4.7 GB
GGUF
LI
Cydonia 22B v1.1
Lite · mradermacher
Params22.2B
Context128K
Q4_K_M13.3 GB
GGUF
LI
0x lite
Lite · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
LI
Lite Oute 1 300M Instruct
Lite · RichardErkhov
Params300M
Context4K
Q4_K_M0.2 GB
GGUF
LI
gguf Lite Oute 1 300M Instruct
Lite · Felladrin
Params300M
Context4K
Smallest0.2 GB
GGUF
LI
Lite-Oute-1-65M-Instruct
Lite · OuteAI
Params65M
Context2K
Q4_K_M0.0 GB
GGUF
LI
ozone ai.0x lite
Lite · DevQuasar-7
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
LI
IlyaGusev/T-lite-instruct-0.1-abliterated
Lite · featherless-ai-quants
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LI
Lite Oute 1 65M Instruct
Lite · mradermacher
Params65M
Context2K
Q4_K_M0.0 GB
GGUF
LI
Lite-Oute-1-65M
Lite · OuteAI
Params65M
Context2K
Q4_K_M0.0 GB
GGUF

About the Lite GGUF models

Lite is represented on ggufmodels.com by 92 GGUF models, quantized by 39 uploaders on Hugging Face. The most downloaded are T lite it 2.1, vllm-d3-lite and T Lite It 1.0. Parameter counts run from 64M to 22.2B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Lite model is between 0.0 to 13.3 GB, which is the quant most people start with. Most files come from mradermacher (18), QuantFactory (7) and NikolayKozloff (6). The quants you will meet most often are Q8_0 (56), Q4_K_M (56), Q5_K_M (53) and Q2_K (49), where the number is how many models offer that quant.

Frequently asked questions

Which Lite GGUF should I download?

The most downloaded Lite GGUF here is T lite it 2.1. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Lite model need?

Q4_K_M files of Lite models on this site range from 0.0 to 13.3 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Lite GGUF files come from?

The most common quantizers here are mradermacher, QuantFactory and NikolayKozloff. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing