Danube GGUF models

133 GGUF models in the Danube family, quantized by 35 uploaders. Sizes run from 514M to 3.96B parameters. The longest trained context is 16K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
DA
danube3-4B
Danube · h2oai
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
DA
danube2-1.8b-CodeFeedback
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
Coding
DA
danube2-1.8b-Synthia-v1.3
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
danube2-1.8b-WizardLM-Evol-V2-Unfiltered
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
danube2-1.8b-Tess-v1.5
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
danube2-1.8b-openhermes
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
Tool use
DA
danube2-1.8b-Neural
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
h2o-danube3-500m-chat
Danube · bartowski
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
h2o-danube2-1.8b-chat
Danube · h2oai
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
arco reflection v4
Danube · QuantFactory
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
danube3-500M
Danube · h2oai
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
h2o-danube3-4b-chat
Danube · bartowski
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
DA
danube2-1.8b-Synthia-v1.3
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
H2O Danube3 500m Base
Danube · mradermacher
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
H2O Danube3 500m Base
Danube · mradermacher
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
h2o-danube3-500m-chat
Danube · BoscoTheDog
Params514M
Context8K
Q4_K_M0.6 GB
GGUF
DA
H2O Danube3.1 4b Chat
Danube · mradermacher
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
DA
H2O Danube2 1.8b Chat
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
H2O Danube3 4b Base
Danube · mradermacher
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
DA
h2o-danube3-500m-chat
Danube · BoscoTheDog
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
H2O Danube 1.8b Chat
Danube · mradermacher
Params1.83B
Context16K
Q4_K_M1.1 GB
GGUF
DA
H2O Danube 1.8b Base
Danube · mradermacher
Params1.83B
Context16K
Q4_K_M1.1 GB
GGUF
DA
Danube3 4b 4chan HESOYAM 2510
Danube · adamo1139
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
DA
H2O Danube3.1 4b Chat
Danube · mradermacher
Params3.96B
Context8K
Q4_K_M2.4 GB
GGUF
DA
h2o-danube2-1.8b-chat
Danube · bartowski
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
H2O Danube2 1.8b Base
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
DA
h2o danube3 500m chat
Danube · DevQuasar-4
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
DA
danube2 upscale 1.7
Danube · mradermacher
Params2.25B
Context8K
Q4_K_M1.4 GB
Roleplay
DA
H2O Danube 1.8b Sft
Danube · mradermacher
Params1.83B
Context16K
Q4_K_M1.1 GB
GGUF
DA
H2O Danube3 500m Base
Danube · RichardErkhov
Params514M
Context8K
Q4_K_M0.3 GB
GGUF

About the Danube GGUF models

Danube is represented on ggufmodels.com by 133 GGUF models, quantized by 35 uploaders on Hugging Face. The most downloaded are danube3-4B, danube2-1.8b-CodeFeedback and danube2-1.8b-Synthia-v1.3. Parameter counts run from 514M to 3.96B, and the longest trained context window is 16K tokens.

A Q4_K_M file of a Danube model is between 0.3 to 4.8 GB, which is the quant most people start with. Most files come from mradermacher (43), Felladrin (9) and adamo1139 (8). The quants you will meet most often are Q4_K_M (95), Q6_K (88), Q5_K_M (84) and Q2_K (82), where the number is how many models offer that quant.

Frequently asked questions

Which Danube GGUF should I download?

The most downloaded Danube GGUF here is danube3-4B. 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 Danube model need?

Q4_K_M files of Danube models on this site range from 0.3 to 4.8 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 Danube GGUF files come from?

The most common quantizers here are mradermacher, Felladrin and adamo1139. 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