Instructions to use groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8")
model = AutoModelForCausalLM.from_pretrained("groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8

SGLang

How to use groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8 with Docker Model Runner:
```
docker model run hf.co/groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8
```

Quantized using the default exllamav3 (0.0.25) quantization process.

Original model: https://huggingface.co/ConicCat/Qwen3.5-27B-Writer
exllamav3: https://github.com/turboderp-org/exllamav3

ConicCat/Qwen3.5-27B-Writer

A writing & roleplay finetune of Qwen3.5 27B. The primary emphasis is on writing quality as it strongly generalizes across both domains. This model is also trained from ConicCat/Qwen3.5-Antirep-27B to mitigate repetition issues.

The basic idea is to use a curriculum learning setup to overcome the lack of high quality roleplay data by first training on lower quality roleplay data, then training on higher quality writing data. Starting from ConicCat/Qwen3.5-Antirep-27B, the model was trained on a roughly equal mixture of instruct / roleplay / writing data for three epochs. The model was then trained for eleven epochs on a smaller dataset of short story anthologies by critically acclaimed authors.

Recommended Settings

Chatml template with <think>\n\n</think> or {{char}}: prefill. Only non-thinking was trained, but thinking probably still works.
temperature = 0.7
top_p = 0.95
I do not recommend using high rep pen values like Qwen suggests for the base model. rep_pen = 1.05 or a moderate dry setting should suffice.
For quants, Q4_K_M runs well with ~100k context on 24GB Vram
IQ4_XS should fit on 16GB Vram with about 20-24k context with the vulkan backend, although it's pretty tight and may require some fiddling around with open programs e.t.c.

Datasets

ConicCat/AntiRep to mitigate repetitition.
internlm/Condor-SFT-20K for instruct; even though instruct capabilities are not the primary focus, adding some instruct data helps mitigate forgetting and maintains general intellect and instruction following capabilites.
PJMixers-Dev/C2-Logs-Sonnet-4.5-all for roleplay. Pretty much exactly what it says on the tin, the venerable C2 logs with the last turn regenerated by Sonnet 4.5 and refusals removed.
ConicCat/Gutenberg-SFT. A reformatted version of the original Gutenberg DPO dataset by jondurbin for SFT with some slight augmentation to address many of the samples being overly long.
A dataset of short story anthologies. Unfortunately, I am unable to release this set as all of the data is under copyright.

Downloads last month: 33

Safetensors

Model size

10B params

Tensor type

F16

I16

BF16

F32

Model tree for groxaxo/Qwen3.5-27B-Writer-exl3-5bpw-hb8

Base model

Qwen/Qwen3.5-27B

Finetuned

ConicCat/Qwen3.5-27B-Writer

Quantized

(9)

this model