AI-TAVS/Qwen3.8-turbo:27b

AI-TAVS/ Qwen3.8-turbo:27b

14 Downloads Updated 6 hours ago

The strongest, smartest open source multi-stage model fine tune for consumer hardware ever and BUILT on consumer hardware via Unsloth.

vision 27b

ollama run AI-TAVS/Qwen3.8-turbo:27b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "AI-TAVS/Qwen3.8-turbo:27b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='AI-TAVS/Qwen3.8-turbo:27b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'AI-TAVS/Qwen3.8-turbo:27b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 6 hours ago

6 hours ago

52c676fd536e · 19GB ·

model

archqwen35

parameters26.9B

quantizationQ4_K_M

18GB

projector

archclip

parameters461M

quantizationF16

928MB

Readme

The strongest, smartest open source multi-stage model fine tune for consumer hardware ever and BUILT on consumer hardware via Unsloth.

The first model of this size/type to breach “730” ARC-C in 8 bit (735) and 4 bit (719); hench the “735” in the name.

This model has ¹⁄₅ (as low as ¹⁄₁₀ in some cases) to ¹⁄₂ the thinking tokens (vs reg Qwen 3.8) across all 3 modes of operation, and it is faster and smarter too created using the COLD FUSION AND FABLE FUSION 711 methods of training.

This is a high detail focused model, with tuning specific to address over reasoning/over thinking and excessive token consumption THEN to take the model to the next level.

This model (both 4 bit and 8 bit) exceeds the base Qwen 3.8 27B in ALL critical 7 benchmarks AND exceeds all 7 benchmarks for Qwen3.6-35B-A3B, Qwen 3.6 27B, and Qwen 3.5 27B.

Detail: https://huggingface.co/DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF