oamazonasgabriel/ qwen3.5-0.8b:q8-8gbGPU

21 Downloads Updated 3 days ago

Qwen3.5 0.8B in Q8_0 quantization. Small, fast model with 262K context, vision, tool use, and thinking capabilities. Optimized for local/edge deployment on constrained hardware.

vision tools thinking

ollama run oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU

curl http://localhost:11434/api/chat \
  -d '{
    "model": "oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 days ago

3 days ago

f3817196d142 · 1.0GB ·

model

archqwen35

·

parameters873M

·

quantizationQ8_0

1.0GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

params

{ "presence_penalty": 1.5, "temperature": 1, "top_k": 20, "top_p": 0.95 }

65B

Readme

Qwen3.5 0.8B - Q8_0 Quantization

A lightweight Qwen3.5 0.8B parameter model in Q8_0 quantization, optimized for local and edge deployment on constrained hardware.

Model Details

Property	Value
Architecture	Qwen3.5
Parameters	873M
Quantization	Q8_0
Context Length	262,144
Embedding Length	1,024
License	Apache 2.0

Capabilities

Completion ‚Äî General text generation
Vision ‚Äî Multimodal image understanding
Tool Use ‚Äî Function calling support
Thinking ‚Äî Chain-of-thought reasoning

Parameters

temperature = 1
top_k = 20
top_p = 0.95
presence_penalty = 1.5

Usage

ollama pull oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU
ollama run oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU

When to Use

Edge devices with limited memory
Quick prototyping and experimentation
Tasks where latency matters more than accuracy
As a Draft Model for speculative decoding with larger Qwen3.5 variants

Limitations

Small parameter count limits complex reasoning and instruction following
Not suitable for tasks requiring deep domain expertise
Vision capabilities are basic compared to larger multimodal models

# Qwen3.5 0.8B - Q8_0 Quantization

A lightweight Qwen3.5 0.8B parameter model in Q8_0 quantization, optimized for local and edge deployment on constrained hardware.

## Model Details

| Property | Value |
|---|---|
| Architecture | Qwen3.5 |
| Parameters | 873M |
| Quantization | Q8_0 |
| Context Length | 262,144 |
| Embedding Length | 1,024 |
| License | Apache 2.0 |

## Capabilities

- **Completion** ‚Äî General text generation
- **Vision** ‚Äî Multimodal image understanding
- **Tool Use** ‚Äî Function calling support
- **Thinking** ‚Äî Chain-of-thought reasoning

## Parameters

```
temperature = 1
top_k = 20
top_p = 0.95
presence_penalty = 1.5
```

## Usage

```bash
ollama pull oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU
ollama run oamazonasgabriel/qwen3.5-0.8b:q8-8gbGPU
```

## When to Use

- Edge devices with limited memory
- Quick prototyping and experimentation
- Tasks where latency matters more than accuracy
- As a Draft Model for speculative decoding with larger Qwen3.5 variants

## Limitations

- Small parameter count limits complex reasoning and instruction following
- Not suitable for tasks requiring deep domain expertise
- Vision capabilities are basic compared to larger multimodal models

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)