org/deepseek-v3-fast

org/ deepseek-v3-fast

92 Downloads Updated 11 months ago

Single file version with (Dynamic Quants) A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

ollama run org/deepseek-v3-fast

curl http://localhost:11434/api/chat \
  -d '{
    "model": "org/deepseek-v3-fast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='org/deepseek-v3-fast',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'org/deepseek-v3-fast',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

4 models

Size

Context

Input

deepseek-v3-fast:latest

244GB · 4K context window · Text · 11 months ago

deepseek-v3-fast:latest

244GB

Text

deepseek-v3-fast:Q2_K_L

latest

244GB · 4K context window · Text · 11 months ago

deepseek-v3-fast:Q2_K_L latest

244GB

Text

deepseek-v3-fast:Q2_K_XS

221GB · 4K context window · Text · 11 months ago

deepseek-v3-fast:Q2_K_XS

221GB

Text

deepseek-v3-fast:Q4_K_M

404GB · 4K context window · Text · 11 months ago

deepseek-v3-fast:Q4_K_M

404GB

Text

Readme

No readme