Captain GGUF models

101 GGUF models in the Captain family, quantized by 15 uploaders. Sizes run from 3M to 32.3B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
CA
Captain Eris Twighlight V0.420 12B
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris Violet V0.420 12B GGUF ARM Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
CA
Captain Eris Diogenes Twilight V0.420 12B GGUF ARM Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
CA
Captain Eris Violet GRPO v0.420 GGUF IQ Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
CA
Captain Eris Violet V0.420 12B i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris Diogenes Twilight V0.420 12B
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
CaPtain 4B
Captain · mradermacher
Params4.84B
Context256K
Q4_K_M3.1 GB
CodingReasoningTool use
CA
Nitral AI Captain Eris Violet GRPO v0.420
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris Twighlight V0.420 12B i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris Violet V0.420 12B
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris Violet V0.420 12B
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris Twighlight V0.420 12B GGUF ARM Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
RoleplayTool use
CA
Captain Eris Violet GRPO v0.420 i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris_Violet V0.420 12B Heretic V2 Fixed
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain_BMO 12B
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris Diogenes Twilight V0.420 12B i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain BMO 0.420 Magnum 12B
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris Twilight V0.420 12B i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris BMO Violent GRPO v0.420 i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Foxfire 12B
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris Violet Toxic Magnum 12B
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris Violet Toxic GRPO other
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris Diogenes Twilight V0.420 12B
Captain · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Nitral-AI/Captain-Eris_Violet-V0.420-12B
Captain · featherless-ai-quants
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris_Violet V0.420 12B Heretic
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain Eris Diogenes Twilight V0.420 12B
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris Twighlight Magnum 12B i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Eris Rebased i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
CA
Captain_Eris_Violet 0.420 Abliterated
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
CA
Captain Violet Mix V0.420 12B i1
Captain · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use

About the Captain GGUF models

Captain is represented on ggufmodels.com by 101 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are Captain Eris Twighlight V0.420 12B, Captain Eris Violet V0.420 12B GGUF ARM Imatrix and Captain Eris Diogenes Twilight V0.420 12B GGUF ARM Imatrix. Parameter counts run from 3M to 32.3B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Captain model is between 3.1 to 19.8 GB, which is the quant most people start with. Most files come from mradermacher (65), bartowski (6) and MaziyarPanahi (5). The quants you will meet most often are Q6_K (89), Q5_K_M (88), Q5_K_S (87) and Q4_K_M (86), where the number is how many models offer that quant.

Frequently asked questions

Which Captain GGUF should I download?

The most downloaded Captain GGUF here is Captain Eris Twighlight V0.420 12B. 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 Captain model need?

Q4_K_M files of Captain models on this site range from 3.1 to 19.8 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 Captain GGUF files come from?

The most common quantizers here are mradermacher, bartowski and MaziyarPanahi. 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