Tromset/ flycoder0.3pro:latest

9 Downloads Updated 1 week ago

vision tools thinking

ollama run Tromset/flycoder0.3pro

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Tromset/flycoder0.3pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Tromset/flycoder0.3pro',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Tromset/flycoder0.3pro',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 week ago

1 week ago

3c88a0a4f7f5 · 18GB

model

archqwen35

·

parameters27.3B

·

quantizationQ4_K_M

17GB

projector

archclip

·

parameters461M

·

quantizationBF16

931MB

license

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

11kB

system

You are FlyCoder 0.3 pro, a coding model running locally on the user's computer through Ollama. You

2.0kB

params

{ "draft_num_predict": 4, "min_p": 0, "num_ctx": 65536, "presence_penalty": 0, "

132B

Readme

FlyCoder 0.3 pro

The strongest FlyCoder, for hard coding work and coding agents, on Macs with 32 GB of memory or more.

ollama run Tromset/flycoder0.3pro

Base	Size	Mac	Context
Qwen3.8 27B (Apache 2.0)	18 GB	32 GB	64K tokens

Works like a senior engineer: pins down the contract, plans multi-file changes, writes the code and the tests that prove it, checks the tricky cases before answering, then tells you how to run the tests.
Built for agents: reads files before editing, makes minimal changes, reports real test output, never runs a destructive command without asking (ollama launch claude --model Tromset/flycoder0.3pro).
Fast for its size: multi-token prediction is on, and 64K tokens of context cost only about 4.4 GB thanks to Qwen3.8’s hybrid attention.

Other sizes: Tromset/flycoder0.3 for 16 GB Macs, Tromset/flycoder0.3fast for 8 GB Macs.

Needs Ollama 0.32.12 or later. Runs on Apple Silicon, Intel Macs, Linux and Windows. Source, benchmark and installer: https://github.com/Tromset/flycoder

# FlyCoder 0.3 pro

The strongest FlyCoder, for hard coding work and coding agents, on Macs with 32 GB of memory or more.

```sh
ollama run Tromset/flycoder0.3pro
```

| Base | Size | Mac | Context |
|---|---|---|---|
| Qwen3.8 27B (Apache 2.0) | 18 GB | 32 GB | 64K tokens |

- **Works like a senior engineer**: pins down the contract, plans multi-file changes, writes the code and the tests that prove it, checks the tricky cases before answering, then tells you how to run the tests.
- **Built for agents**: reads files before editing, makes minimal changes, reports real test output, never runs a destructive command without asking (`ollama launch claude --model Tromset/flycoder0.3pro`).
- **Fast for its size**: multi-token prediction is on, and 64K tokens of context cost only about 4.4 GB thanks to Qwen3.8's hybrid attention.

Other sizes: [`Tromset/flycoder0.3`](https://ollama.com/Tromset/flycoder0.3) for 16 GB Macs, [`Tromset/flycoder0.3fast`](https://ollama.com/Tromset/flycoder0.3fast) for 8 GB Macs.

Needs Ollama 0.32.12 or later. Runs on Apple Silicon, Intel Macs, Linux and Windows.
Source, benchmark and installer: https://github.com/Tromset/flycoder

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