Instructions to use whisperstream/stream-1-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use whisperstream/stream-1-mini with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf whisperstream/stream-1-mini:F16
# Run inference directly in the terminal:
llama cli -hf whisperstream/stream-1-mini:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf whisperstream/stream-1-mini:F16
# Run inference directly in the terminal:
llama cli -hf whisperstream/stream-1-mini:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf whisperstream/stream-1-mini:F16
# Run inference directly in the terminal:
./llama-cli -hf whisperstream/stream-1-mini:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf whisperstream/stream-1-mini:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf whisperstream/stream-1-mini:F16

Use Docker

docker model run hf.co/whisperstream/stream-1-mini:F16

Llama new
LM Studio
Jan

vLLM

How to use whisperstream/stream-1-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "whisperstream/stream-1-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "whisperstream/stream-1-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/whisperstream/stream-1-mini:F16

Ollama
How to use whisperstream/stream-1-mini with Ollama:
```
ollama run hf.co/whisperstream/stream-1-mini:F16
```
Unsloth Desktop
Docker Model Runner
How to use whisperstream/stream-1-mini with Docker Model Runner:
```
docker model run hf.co/whisperstream/stream-1-mini:F16
```

Lemonade

How to use whisperstream/stream-1-mini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull whisperstream/stream-1-mini:F16

Run and chat with the model

lemonade run user.stream-1-mini-F16

List all available models

lemonade list

Atomic Chat

stream-1-mini / NOTICE

lanreal-io

Publish Stream-1 Mini FP32, F16 and Q4_K_M

8a26b93 verified 9 days ago

Raw History Blame Contribute Delete

1.03 kB

Stream-1 Mini by Whisperstream
Copyright 2026 Lanreal Technologies Inc., to the extent copyright subsists
in its contributions.

Based on Qwen/Qwen3-0.6B-Base, Copyright 2024 Alibaba Cloud.
Upstream revision: da87bfb608c14b7cf20ba1ce41287e8de496c0cd
https://huggingface.co/Qwen/Qwen3-0.6B-Base/tree/da87bfb608c14b7cf20ba1ce41287e8de496c0cd

Changes by Lanreal: task-specific supervised fine-tuning for dictation
cleanup, merged adapter weights, separately retained embedding and output
weights, a plain ChatML template without a thinking preamble, associated
configuration and prompts, and GGUF conversion/quantization.

The weights, configuration and tokenizer distribution are modified from
the original upstream distribution. The original Apache-2.0 license is
provided in LICENSE-APACHE-2.0. Stream-1 Mini's additional identification
condition appears in LICENSE, not in this informational notice.

Qwen and Alibaba Cloud are credited as upstream sources. Their names do
not imply endorsement of this release.

	Stream-1 Mini by Whisperstream
	Copyright 2026 Lanreal Technologies Inc., to the extent copyright subsists
	in its contributions.

	Based on Qwen/Qwen3-0.6B-Base, Copyright 2024 Alibaba Cloud.
	Upstream revision: da87bfb608c14b7cf20ba1ce41287e8de496c0cd
	https://huggingface.co/Qwen/Qwen3-0.6B-Base/tree/da87bfb608c14b7cf20ba1ce41287e8de496c0cd

	Changes by Lanreal: task-specific supervised fine-tuning for dictation
	cleanup, merged adapter weights, separately retained embedding and output
	weights, a plain ChatML template without a thinking preamble, associated
	configuration and prompts, and GGUF conversion/quantization.

	The weights, configuration and tokenizer distribution are modified from
	the original upstream distribution. The original Apache-2.0 license is
	provided in LICENSE-APACHE-2.0. Stream-1 Mini's additional identification
	condition appears in LICENSE, not in this informational notice.

	Qwen and Alibaba Cloud are credited as upstream sources. Their names do
	not imply endorsement of this release.