Small GGUF models

73 GGUF models in the Small family, quantized by 44 uploaders. Sizes run from 13M to 221B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SM
Small DS R1
Small · mradermacher
Params221B
Context160K
Q4_K_M133.5 GB
ReasoningTool use
SM
e5-small-v2
Small · ChristianAzinn
Params33M
Context512
Q4_K_M0.0 GB
Embedding
SM
Melta27
Small · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
SM
Small Agentic Model 1.5B
Small · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
SM
Small_Melta27
Small · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
SM
Melta27
Small · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
SM
Small DS R1
Small · mradermacher
Params221B
Context160K
Q4_K_M133.5 GB
ReasoningTool use
SM
small thinker
Small · cortexso
Params3.4B
Context32K
Q4_K_M2.1 GB
Reasoning
SM
T5 Small
Small · layonsan
Params—
Context512
Smallest0.0 GB
GGUF
SM
e5 small v2 i1
Small · mradermacher
Params33M
Context512
Q4_K_M0.0 GB
Embedding
SM
e5 small v2 Q8 0
Small · ggml-org
Params33M
Context512
Smallest0.0 GB
Embedding
SM
E5 Small
Small · mradermacher
Params33M
Context512
Q4_K_M0.0 GB
Embedding
SM
small okaberintaro
Small · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
SM
small okaberintaro i1
Small · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF
SM
small lm3 jack 5000x
Small · harshsingh24
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
SM
E5 Small
Small · mradermacher
Params33M
Context512
Q4_K_M0.0 GB
Embedding
SM
e5 small v2
Small · mradermacher
Params33M
Context512
Q4_K_M0.0 GB
Embedding
SM
Small Talk 1.3
Small · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
SM
T5 Small
Small · noumenalabs
Params61M
Context512
Q4_K_M0.0 GB
GGUF
SM
T5 Small
Small · layonsan
Params61M
Context512
Smallest0.1 GB
GGUF
SM
small test
Small · Serveurperso
Params95M
Context256K
Smallest0.1 GB
Tool useVision
SM
small molecule drugs
Small · Heshiyu
Params8.03B
Context128K
Smallest8.5 GB
ReasoningTool use
SM
Cveparrot
Small · Breakintelligence
Params61M
Context512
Smallest0.1 GB
GGUF
SM
Small Hikari v0.3 Q8 0
Small · Rookied
Params2.61B
Context8K
Smallest2.8 GB
GGUF
SM
T5 Small
Small · cahaj
Params77M
Context512
Smallest0.2 GB
GGUF
SM
Small Math
Small · Stormtrooperaim
Params596M
Context40K
Smallest0.6 GB
Reasoning
SM
T5 Small
Small · Jaewoo49
Params61M
Context512
Smallest0.0 GB
GGUF
SM
T5 Small
Small · jagan546
Params61M
Context512
Smallest0.1 GB
GGUF
SM
T5 Small
Small · Jaewoo49
Params61M
Context512
Q4_K_M0.0 GB
GGUF
SM
Mt5 Small
Small · Plasmoxy
Params300M
Context512
Q4_K_M0.2 GB
GGUF

About the Small GGUF models

Small is represented on ggufmodels.com by 73 GGUF models, quantized by 44 uploaders on Hugging Face. The most downloaded are Small DS R1, e5-small-v2 and Melta27. Parameter counts run from 13M to 221B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Small model is between 0.0 to 133.5 GB, which is the quant most people start with. Most files come from mradermacher (13), layonsan (6) and jukkim046 (4). The quants you will meet most often are Q4_K_M (35), Q8_0 (27), Q2_K (19) and F16 (19), where the number is how many models offer that quant.

Frequently asked questions

Which Small GGUF should I download?

The most downloaded Small GGUF here is Small DS R1. 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 Small model need?

Q4_K_M files of Small models on this site range from 0.0 to 133.5 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 Small GGUF files come from?

The most common quantizers here are mradermacher, layonsan and jukkim046. 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