Marco GGUF models

121 GGUF models in the Marco family, quantized by 40 uploaders. Sizes run from 4M to 17.4B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MA
ms marco MiniLM L6 v2 Q8 0
Marco · sinjab
Params23M
Context512
Smallest0.0 GB
CodingEmbedding
MA
Marco Mini Instruct
Marco · mradermacher
Params17.3B
Context32K
Q4_K_M10.5 GB
Reasoning
MA
Marco o1
Marco · bartowski
Params7.6B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco DeepResearch 8B
Marco · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
GGUF
MA
Marco Nano Instruct
Marco · mradermacher
Params8B
Context32K
Q4_K_M5.4 GB
Reasoning
MA
ms marco MiniLM L 6 v2
Marco · cstr
Params23M
Context512
Smallest0.0 GB
CodingEmbedding
MA
Marco Mini Global Base
Marco · mradermacher
Params17.4B
Context32K
Q4_K_M10.6 GB
GGUF
MA
Marco Nano Instruct 1-bit (ternary, TQ1_0)
Marco · RegalInvader
Params8B
Context32K
Smallest2.2 GB
Tool use
MA
Marco Nano Base
Marco · mradermacher
Params8.16B
Context32K
Q4_K_M5.5 GB
GGUF
MA
Marco MT Algharb
Marco · mradermacher
Params14.8B
Context4K
Q4_K_M9.0 GB
GGUF
MA
Marco o1
Marco · QuantFactory
Params7.6B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco Mini Instruct
Marco · mradermacher
Params17.3B
Context32K
Q4_K_M10.5 GB
ReasoningTool use
MA
Marco DeepResearch 8B
Marco · ATH-MaaS
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
MA
Marco Mini Base
Marco · mradermacher
Params17.4B
Context32K
Q4_K_M10.6 GB
Tool use
MA
ms marco MiniLM L 12 v2
Marco · cstr
Params33M
Context512
Smallest0.0 GB
CodingEmbedding
MA
Marco LLM SEA
Marco · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
MA
Marco Nano Instruct
Marco · mradermacher
Params8B
Context32K
Q4_K_M5.4 GB
ReasoningTool use
MA
Marco O1
Marco · prithivMLmods
Params7.6B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco o1 i1
Marco · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco DeepResearch 8B
Marco · ATH-MaaS
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
MA
Marco o1
Marco · mmnga
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco o1
Marco · Alcoft
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco Nano INSTRUCT 8B A0.6B V2
Marco · mradermacher
Params8B
Context32K
Q4_K_M5.4 GB
Tool use
MA
marco o1 uncensored i1
Marco · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco o1
Marco · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco DeepResearch 8B
Marco · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
MA
Marco o1 abliterated i1
Marco · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
MA
Marco LLM AR V2
Marco · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
MA
Marco LLM AR
Marco · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
MA
Marco MT Algharb
Marco · mradermacher
Params14.8B
Context4K
Q4_K_M9.0 GB
GGUF

About the Marco GGUF models

Marco is represented on ggufmodels.com by 121 GGUF models, quantized by 40 uploaders on Hugging Face. The most downloaded are ms marco MiniLM L6 v2 Q8 0, Marco Mini Instruct and Marco o1. Parameter counts run from 4M to 17.4B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Marco model is between 0.0 to 10.6 GB, which is the quant most people start with. Most files come from mradermacher (47), sinjab (22) and keisuke-miyako (3). The quants you will meet most often are Q4_K_M (78), Q2_K (66), Q8_0 (64) and Q6_K (64), where the number is how many models offer that quant.

Frequently asked questions

Which Marco GGUF should I download?

The most downloaded Marco GGUF here is ms marco MiniLM L6 v2 Q8 0. 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 Marco model need?

Q4_K_M files of Marco models on this site range from 0.0 to 10.6 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 Marco GGUF files come from?

The most common quantizers here are mradermacher, sinjab and keisuke-miyako. 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