Instructions to use bloomsirenix/q3mds-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bloomsirenix/q3mds-8b with Transformers:

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

pipe = pipeline("text-generation", model="bloomsirenix/q3mds-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bloomsirenix/q3mds-8b")
model = AutoModelForCausalLM.from_pretrained("bloomsirenix/q3mds-8b", device_map="auto")
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 bloomsirenix/q3mds-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bloomsirenix/q3mds-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bloomsirenix/q3mds-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bloomsirenix/q3mds-8b

SGLang

How to use bloomsirenix/q3mds-8b 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 "bloomsirenix/q3mds-8b" \
    --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": "bloomsirenix/q3mds-8b",
		"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 "bloomsirenix/q3mds-8b" \
        --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": "bloomsirenix/q3mds-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bloomsirenix/q3mds-8b with Docker Model Runner:
```
docker model run hf.co/bloomsirenix/q3mds-8b
```

q3mds-8b-merged

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using models/Qwen3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

# Q3MDS-8B hybrid merge — DARE-TIES over Qwen/Qwen3-8B
#
# All four ingredients share the Qwen3-8B architecture (36 layers, hidden 4096)
# and the Qwen3 tokenizer, so task vectors (model - base) are meaningful.
#
# Tune `weight` (how much of each delta survives) and `density` (fraction of
# delta kept after DARE drop + TIES pruning). density 0.5-0.7 is the sane range.

merge_method: dare_ties
base_model: models/Qwen3-8B
dtype: bfloat16
tokenizer_source: Qwen/Qwen3-8B

models:
  - model: models/Qwen3-8B                # instruct anchor / chat quality
    parameters:
      weight: 0.30
      density: 0.60
  - model: models/DeepSeek-R1-0528-Qwen3-8B   # R1-0528 reasoning, distilled by DeepSeek into Qwen3-8B
    parameters:
      weight: 0.35
      density: 0.60
  - model: models/Qwen3-8B-ABC   # agentic backend coding + tool use
    parameters:
      weight: 0.25
      density: 0.60
  - model: models/OpenCodeEdit-Qwen3-8B        # code-edit format tasks
    parameters:
      weight: 0.10
      density: 0.60

parameters:
  normalize: true
  int8_mask: true

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for bloomsirenix/q3mds-8b

OpenMOSS-Team/Qwen3-8B-ABC

Qwen/Qwen3-8B

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

zkzhang88/OpenCodeEdit-Qwen3-8B

Merge model

this model

Paper for bloomsirenix/q3mds-8b

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 38