Leaderboard / OpenBMB (MiniCPM)
MiniCPM5 1B
OpenBMB (MiniCPM) · MiniCPM5 · released 2026-05-21 · data checked 2026-11-01
MiniCPM5 1B is a 1.1B-parameter dense model from OpenBMB (MiniCPM) (China), released 2026-05-21 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 1.4 GB of memory at 4-bit with an 8K-token context.
Small LM Index
—
Needs 2 core benchmarks (has 0)
Parameters
1.1B
Dense
Price per 1M tokens
—
No hosted API on OpenRouter; self-host
Context window
131K
tokens
Benchmarks
Each bar shows this model's score. The tick marks the best tiny model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- OpenBMB (MiniCPM) (CN · China)
- Architecture
- Dense transformer
- Total parameters
- 1.1B
- Active parameters
- All (dense)
- Size class
- Tiny
- Context window
- 131K tokens
- Input modalities
- text
- Reasoning
- Hybrid (thinking on/off)
- License
- Apache-2.0
- Openness
- Open weights
- Memory to run
- ~1.4 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 267.2K downloads (30 days) · 1.2K likes
Compare with
- MiniCPM5 1B vs Gemma 3 1B (1B, index 6.1)
- MiniCPM5 1B vs LFM2.5 1.2B Thinking (1.2B, index 30.1)
- MiniCPM5 1B vs LFM2.5 1.2B Instruct (1.2B, index 20.6)
Sources
Something wrong here? Report it.
Run it locally
No GGUF build from a well-known publisher yet.
MLX (Mac)
pip install -U mlx-lm
mlx_lm.chat --model mlx-community/MiniCPM5-1B-OptiQ-4bitvLLM (GPU server)
vllm serve openbmb/MiniCPM5-1BFull-precision weights, for a server GPU.
Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context | 131K context |
|---|---|---|---|
| 16-bit F16 | 2.8 GB | 3.5 GB | 5.9 GB |
| 8-bit Q8_0 | 1.8 GB | 2.5 GB | 4.9 GB |
| 4-bit Q4_K_M | 1.3 GB | 2.0 GB | 4.4 GB |