LESSTHANSUPER/DARKEST_UNIVERSE-Mistral

LESSTHANSUPER/ DARKEST_UNIVERSE-Mistral_Nemo-29b

1,414 Downloads Updated 3 months ago

Uncensored storytelling model based on Mistral Nemo. Made by DavidAU (Huggingface).

tools

ollama run LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K

curl http://localhost:11434/api/chat \
  -d '{
    "model": "LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K

Codex ollama launch codex --model LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K

OpenCode ollama launch opencode --model LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K

OpenClaw ollama launch openclaw --model LESSTHANSUPER/DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K

Models

View all →

Name

8 models

Size

Context

Input

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K

11GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q2_K

11GB

1000K

Text

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q3_K_S

13GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q3_K_S

13GB

1000K

Text

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q3_K_M

14GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q3_K_M

14GB

1000K

Text

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q4_K_S

17GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q4_K_S

17GB

1000K

Text

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q5_K_S

20GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:Q5_K_S

20GB

1000K

Text

DARKEST_UNIVERSE-Mistral_Nemo-29b:IQ3_XXS

11GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:IQ3_XXS

11GB

1000K

Text

DARKEST_UNIVERSE-Mistral_Nemo-29b:IQ3_S

13GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:IQ3_S

13GB

1000K

Text

DARKEST_UNIVERSE-Mistral_Nemo-29b:IQ4_XS

16GB · 1000K context window · Text · 3 months ago

DARKEST_UNIVERSE-Mistral_Nemo-29b:IQ4_XS

16GB

1000K

Text

Readme

DARKEST UNIVERSE / I-MATRIX / 29B / I-QUANT

Huggingface user DavidAU has created some good MoE models of many sizes, focusing on prose, well made descriptions, and the horror genre. Notable models being the smaller “Hell California,” and the larger, non-MoE “Darkest Planet”. This non-MoE model is one of their larger models made. To stuff as many parameters in as little VRAM as possible, weighted K and I-quants will be listed.

Note that I-quants forfeit some token generation speed relative to K-quants in exchange for storage efficiency. The small 3-bit quants, I or K, are recommended for 16GB GPUs. These models were taken from GGUF formats from Huggingface.

Original model (DavidAU):

GGUF weighted quantizations (mradermacher):