fauxpaslife/PentaCoder-9B

fauxpaslife/ PentaCoder-9B:latest

11 Downloads Updated 21 hours ago

The foundational weights of Qwen/Qwen3.5-9B with selected specialization to maximize coding + agentic work at a small size using distillation/donar weights. ~7 GB loaded. Q4_K_M.

tools thinking

ollama run fauxpaslife/PentaCoder-9B

curl http://localhost:11434/api/chat \
  -d '{
    "model": "fauxpaslife/PentaCoder-9B",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='fauxpaslife/PentaCoder-9B',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'fauxpaslife/PentaCoder-9B',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 21 hours ago

21 hours ago

1b033d7dd92a · 5.6GB

model

archqwen35

parameters8.95B

quantizationQ4_K_M

5.6GB

template

{{- if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }} {{- if .Tools }}<|im_start|>sy

1.6kB

params

{ "stop": [ "<|im_end|>", "</tool_call>" ], "temperature": 0.6, "top

101B

Readme

Found a bug - or a version request?: https://deltakitsune.org/report-a-bug/

Model: PentaCoder 9B by Pragmaticcs, imported using delta : kitsune : forge.
Hugging Face GGUF: https://huggingface.co/pragmaticcs/PentaCoder-9B-GGUF#recommended-generation-parameters
Hugging Face FP16: https://huggingface.co/pragmaticcs/PentaCoder-9B
Base Model: Qwen 3.5 with weights from distilled finetunes
Info: ~7 GB loaded. Q4_K_M.

Example of use in Ollama:

Technical/Information from the author’s page:

### I imported using the suggested settings:

Found a bug - or a version request?: [https://deltakitsune.org/report-a-bug/](https://deltakitsune.org/report-a-bug/)

**Model**: PentaCoder 9B by Pragmaticcs, imported using delta : kitsune : forge. 
**Hugging Face GGUF**: [https://huggingface.co/pragmaticcs/PentaCoder-9B-GGUF#recommended-generation-parameters](https://huggingface.co/pragmaticcs/PentaCoder-9B-GGUF#recommended-generation-parameters) 
**Hugging Face FP16**: [https://huggingface.co/pragmaticcs/PentaCoder-9B](https://huggingface.co/pragmaticcs/PentaCoder-9B) 
**Base Model**: Qwen 3.5 with weights from distilled finetunes 
**Info**: ~7 GB loaded. Q4_K_M.

![image.png](/assets/fauxpaslife/PentaCoder-9B/71fd200f-a07c-481b-8b99-2cf28abad7af)

_**Example of use in Ollama**_: 
![Screenshot 2026-10-17 142309.png](/assets/fauxpaslife/PentaCoder-9B/55a1f36f-8eff-48ae-bf85-992d8e944f13)

**_Technical/Information from the author's page_**:

![image.png](/assets/fauxpaslife/PentaCoder-9B/0e0f5ccb-ed09-4601-b848-13f17f46648b)

![Screenshot 2026-10-17 143233.png](/assets/fauxpaslife/PentaCoder-9B/8b4dd662-b07b-4fe7-9d8e-e59d5ed68eb5)

**### I imported using the suggested settings:**

![Screenshot 2026-10-17 143342.png](/assets/fauxpaslife/PentaCoder-9B/298245c5-38c9-4794-ba84-5e81cc6a9c31)

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