MiniCPM5 1B
MiniCPM5-1B is the first release in the MiniCPM5 series, a dense 1B-parameter causal language model built for on-device, local deployment, and resource-constrained scenarios. It is based on the standard LlamaForCausalLM architecture and supports English and Chinese. According to its official model card, it reaches 1B-class open-source SOTA within its comparison set, with advantages noted in agentic tool use, code generation, and difficult reasoning. It provides native long-context support and a hybrid reasoning mode via a built-in `` chat template that can be switched with `enable_thinking`. The checkpoint is licensed under Apache-2.0 and is available alongside related SFT, Base, GGUF, and MLX variants.
At a glance
- Parameters
- 1.08B
- Architecture
- llama
- Context length
- 131,072
- License
- apache-2.0
- Disk space
- 2 GB
- Software
- SGLang, vLLM, Transformers, llama.cpp, SGLang, vLLM
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Local assistants where a compact model is preferred
- Coding agent workflows
- Tool-use and agentic tool-calling scenarios
- Reasoning scenarios, including both fast assistant and deliberate reasoning modes
- On-device or edge deployment in resource-constrained environments
Tradeoffs
- No performance, compatibility, or numerical hardware requirements are stated beyond the supplied facts
- The model card does not specify supported runtime backends for this checkpoint beyond referenced variant formats
- No license information is provided beyond Apache-2.0 for this model
- No testing or evaluation results are provided in the supplied facts
- The model card does not specify limitations of the hybrid reasoning mode or long-context behavior
Ways to run it
SGLang · Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
python -m sglang.launch_server --model-path openbmb/MiniCPM5-1B --port 30000vLLM · Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
vllm serve openbmb/MiniCPM5-1B --port 8000Transformers · See official guide
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "openbmb/MiniCPM5-1B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}]
inputs = tokenizer.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
enable_thinking=False,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))llama.cpp · Windows, macOS, Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
llama-server -m MiniCPM5-2B-F16.gguf -a MiniCPM5-2B --port 8080 -ngl 99 -c 8192 --jinjaSGLang · Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
python -m sglang.launch_server --model-path openbmb/MiniCPM5-2B --port 30000vLLM · Linux
Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.
vllm serve openbmb/MiniCPM5-2B --port 8000Explore its uses
Keep exploring
Bonsai 2 · 27B
A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.
DeepSeek V4.1 Flash
A multimodal reasoning model with a compressed key-value cache, published as open weights.
Qwen3.8
Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.