bazobehram/qwen3.5-flash-27b

bazobehram/ qwen3.5-flash-27b

6,265 Downloads Updated 1 month ago

ollama run bazobehram/qwen3.5-flash-27b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "bazobehram/qwen3.5-flash-27b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='bazobehram/qwen3.5-flash-27b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'bazobehram/qwen3.5-flash-27b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

1 model

Size

Context

Input

qwen3.5-flash-27b:latest

17GB · 256K context window · Text · 1 month ago

qwen3.5-flash-27b:latest

17GB

256K

Text

Readme

# qwen3.5-flash-27b (Ollama)

Fast-tuned Qwen3.5 27B profile for Ollama.

## Model
- Name: `bazobehram/qwen3.5-flash-27b`
- Base: Qwen3.5 27B (GGUF Q4_K_M)
- Size: ~16 GB
- Tuned runtime defaults:
  - `num_ctx 4096`
  - `num_batch 32`
  - `temperature 0.6`
  - `top_k 20`
  - `top_p 0.95`

## Quick Start

```bash
ollama pull bazobehram/qwen3.5-flash-27b
ollama run bazobehram/qwen3.5-flash-27b "Write one sentence about Bitcoin."

API Example

curl http://localhost:11434/api/generate \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bazobehram/qwen3.5-flash-27b",
    "prompt": "Write one sentence about Bitcoin.",
    "stream": false
  }'

Notes

If you get architecture/compatibility errors, update Ollama to a build that supports qwen3.5.
First response can be slower due to model load/warmup.

”`