All GGUF models

79 GGUF models in the All family, quantized by 56 uploaders. Sizes run from 23M to 17.3B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
AL
all-MiniLM-L6-v2
All · second-state
Params23M
Context512
Q4_K_M0.0 GB
Embedding
AL
all-MiniLM-L6-v2
All · leliuga
Params23M
Context512
Q4_K_M0.0 GB
CodingEmbedding
AL
all-MiniLM-L12-v2
All · leliuga
Params33M
Context512
Q4_K_M0.0 GB
CodingEmbedding
AL
all MiniLM L6 v2 BE
All · taronaeo
Params23M
Context512
Q4_K_M0.0 GB
GGUF
AL
all MiniLM L6 v2
All · cstr
Params23M
Context512
Smallest0.0 GB
Embedding
AL
all-MiniLM-L6-v2
All · stratalab-org
Params23M
Context512
Q4_K_M0.0 GB
CodingEmbedding
AL
all-MiniLM-L6-v2
All · Mungert
Params23M
Context512
Q4_K_M0.0 GB
CodingEmbedding
AL
Q38B All Images Fully Trained
All · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
AL
Q38B All Images
All · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
AL
all MiniLM L6 v2 Q8 0
All · sudomoniker
Params23M
Context512
Smallest0.0 GB
CodingEmbedding
AL
elyza 8b test
All · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AL
all MiniLM L6 v2 Q4 K M
All · groonga
Params23M
Context512
Q4_K_M0.0 GB
CodingEmbedding
AL
all MiniLM L6 v1
All · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
Embedding
AL
all-MiniLM-L6-v2
All · LLukas22
Params23M
Context512
Smallest0.0 GB
CodingEmbedding
AL
all MiniLM L6 v1 i1
All · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
Embedding
AL
all MiniLM L12 v2
All · cstr
Params33M
Context—
Smallest0.0 GB
GGUF
AL
all mpnet base v2
All · cstr
Params109M
Context514
Smallest0.1 GB
Embedding
AL
all MiniLM L6 v2
All · thlurte
Params23M
Context512
Q4_K_M0.0 GB
GGUF
AL
all MiniLM L6 v2
All · infosecinnovations
Params23M
Context512
Smallest0.0 GB
Embedding
AL
All MiniLM Pubmed
All · mradermacher
Params23M
Context512
Q4_K_M0.0 GB
Embedding
AL
all wrong answers
All · sachinstag7
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
AL
all MiniLM L6 v2 Q8 0
All · huoxu
Params23M
Context512
Smallest0.0 GB
CodingEmbedding
AL
all MiniLM L6 v2 f16
All · caliex
Params23M
Context512
Smallest0.0 GB
GGUF
AL
minilm l6 v2 mnn
All · darkmaniac7
Params23M
Context512
Smallest0.0 GB
Embedding
AL
all MiniLM L6 v2
All · smarttasks
Params23M
Context512
Q4_K_M0.0 GB
Embedding
AL
all MiniLM L6 v2
All · s3dev-ai
Params23M
Context512
Q4_K_M0.0 GB
Embedding
AL
gguf Q8 0 all MiniLM L6 v2
All · Felladrin
Params23M
Context512
Smallest0.0 GB
CodingEmbedding
AL
all-MiniLM-L6-v2
All · Jarbas
Params23M
Context512
Q4_K_M0.0 GB
CodingEmbedding
AL
all-MiniLM-L6-v2
All · gaianet
Params23M
Context512
Smallest0.0 GB
Embedding
AL
OGAI Embedder
All · GainEnergy
Params23M
Context512
Smallest0.0 GB
Embedding

About the All GGUF models

All is represented on ggufmodels.com by 79 GGUF models, quantized by 56 uploaders on Hugging Face. The most downloaded are all-MiniLM-L6-v2, all-MiniLM-L6-v2 and all-MiniLM-L12-v2. Parameter counts run from 23M to 17.3B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a All model is between 0.0 to 5.0 GB, which is the quant most people start with. Most files come from mradermacher (7), sheldonrobinson (4) and devisri050 (4). The quants you will meet most often are Q8_0 (37), Q4_K_M (33), F16 (22) and Q5_K_M (17), where the number is how many models offer that quant.

Frequently asked questions

Which All GGUF should I download?

The most downloaded All GGUF here is all-MiniLM-L6-v2. 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 All model need?

Q4_K_M files of All models on this site range from 0.0 to 5.0 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 All GGUF files come from?

The most common quantizers here are mradermacher, sheldonrobinson and devisri050. 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