Mini GGUF models

101 GGUF models in the Mini family, quantized by 49 uploaders. Sizes run from 18M to 30.5B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MI
s1 mini
Mini · superwhisper
Params752M
Context40K
Q4_K_M0.5 GB
GGUF
MI
vllm-d3-mini
Mini · ggml-org
Params4.84B
Context256K
Q4_K_M3.7 GB
Vision
MI
Mini-Omni2
Mini · cstr
Params782M
Context—
Smallest1.1 GB
GGUF
MI
Mini Hydra
Mini · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
MI
mini magnum 12b v1.1
Mini · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mini Magnum 12b v1.1
Mini · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mini Magnum 12b v1.1
Mini · InferenceIllusionist
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mini Magnum 12b v1.1
Mini · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mini Hydra
Mini · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
MI
mini magnum 12b v1.1
Mini · backyardai
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
openaudio
Mini · calcuis
Params695M
Context—
Q4_K_M1.0 GB
GGUF
MI
A11Oy_Mini_R2
Mini · SZLHOLDINGS
Params773M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
MI
mini-agent-v2
Mini · F-A-I-L
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
MI
Mini cpm vikhr
Mini · mradermacher
Params2.78B
Context2K
Q4_K_M1.9 GB
GGUF
MI
Mini Pandor Base
Mini · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
MI
mini Cogito R1 i1
Mini · mradermacher
Params1.78B
Context24K
Q4_K_M1.1 GB
ReasoningTool use
MI
S1 ASR Cleanup
Mini · danielrosehill
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
MI
Mini Spyra V.2.1
Mini · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
minirecord_mini_synatra_7b_02
Mini · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
P3 mini v3
Mini · mradermacher
Params3.82B
Context4K
Q4_K_M2.3 GB
GGUF
MI
Mini Magnum Unboxed 12B
Mini · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mini AGI 4B
Mini · mradermacher
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
MI
d3-mini Artemis Q5_K_S
Mini · turintech
Params4.84B
Context256K
Smallest3.3 GB
ReasoningTool use
MI
Mini DPO test02
Mini · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
RP Mini 3B
Mini · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Roleplay
MI
Mini Spyra V.1.3
Mini · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
S1 Mini
Mini · mradermacher
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
MI
Mini cpm vikhr i1
Mini · mradermacher
Params2.78B
Context2K
Q4_K_M1.9 GB
GGUF
MI
Mini Magnum 12b v1.1
Mini · RichardErkhov
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mini Art 1.0
Mini · Dev4285
Params630M
Context32K
Q4_K_M0.5 GB
RoleplayTool use

About the Mini GGUF models

Mini is represented on ggufmodels.com by 101 GGUF models, quantized by 49 uploaders on Hugging Face. The most downloaded are s1 mini, vllm-d3-mini and Mini-Omni2. Parameter counts run from 18M to 30.5B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Mini model is between 0.4 to 18.6 GB, which is the quant most people start with. Most files come from mradermacher (31), Kwokou (6) and mbahrsnc (4). The quants you will meet most often are Q4_K_M (67), Q8_0 (60), Q6_K (54) and Q5_K_M (52), where the number is how many models offer that quant.

Frequently asked questions

Which Mini GGUF should I download?

The most downloaded Mini GGUF here is s1 mini. 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 Mini model need?

Q4_K_M files of Mini models on this site range from 0.4 to 18.6 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 Mini GGUF files come from?

The most common quantizers here are mradermacher, Kwokou and mbahrsnc. 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