OpenBMB · MiniCPM
MiniCPM5 2B
Verified by Badgr · ServeMiniCPM5 2B is a 2.5B chat and text-generation model available through supported Badgr execution routes.
Last validated or meaningfully updated: 2026-10-10
✓ Verified by Badgr · vLLM · Serve
Last verified 2026-10-10
badgr serve openbmb/MiniCPM5-2B --gpu auto --funding paid --max-cost 2 --startup-timeout 40 --vllm-arg --trust-remote-code- GPU
- NVIDIA RTX A4000Reported by the provider, not confirmed inside the container
- Time to verified
- 220s
- Deployment
- dep-fa899e4ddb
- ✓ vLLM started
- ✓ Badgr's inference check returned a completion
- ✓ final_state = VERIFIED
- ✓ Teardown completed
Served with --trust-remote-code. The first GPU offer had no capacity and Badgr moved to the next one. An earlier attempt without --startup-timeout ran out of its default startup window.
Real cross-provider fallback: 1 other GPU offer didn’t come up in time before this run landed on the GPU shown above and verified. The same automatic retry a live customer job gets.
Raw evidence
final_state=VERIFIED failure_class=None providers_tried=2 spend_usd=0.0132 elapsed=219.9s
Run from Badgr's local development environment. Documents that this deployment path works end-to-end for this model.
Availability
Not yet Badgr AI API
Not currently validated
✓ Dedicated endpoint
Available through Badgr
✓ Custom GPU deployment
Available through Badgr
Deployment profile
- Architecture
- LlamaForCausalLM
- Licence
- Apache-2.0
- Minimum VRAM
- ~9GB
- Context
- 128K tokens
Recommended: RTX 4090 24GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.
Model identity
- Languages
- en, zh
- Updated
- 11 days ago
- HuggingFace revision
- f97400052a
Popularity and trust
Downloads (last month)
1.3M
Likes
1.7K
Spaces using this model
28
Files and formats
Weight formats
Safetensors
Repository files
11
Chat template
Available
GPU deployment scenarios
Estimated from parameter count and quantisation. This model's one verified real run was reported by the provider as NVIDIA RTX A4000, which isn't one of the tiers below.
Testing
RTX 4090 24GB
Short context, low concurrency
Small production
L40S 48GB
8K context, 1-4 concurrent requests
Higher throughput
A100 80GB
32K context, continuous batching
Large production
RTX 4090 24GB
Higher concurrency
Estimated — multimodal inputs, long context, and concurrency all increase real VRAM use beyond this estimate.
Also runs well on L40S 48GB, A100 40GB. Available in United States, Europe.
Serving compatibility
| Runtime | Status | Notes |
|---|---|---|
| vLLM | Verified by Badgr | Confirmed by a real badgr serve run (deployment dep-fa899e4ddb) |
| Transformers | Declared by source | Basic fallback |
| llama.cpp | Requires GGUF conversion | No GGUF weights found in repo |
| SGLang | Unknown | Not evaluated |
| Ollama | Unknown | Not evaluated |
| Diffusers | Unknown | Not evaluated |
| PyTorch | Unknown | Not evaluated |
| TensorRT-LLM | Unknown | Conversion may be required |
| TGI | Unknown | Not evaluated |
Ready-to-run Badgr configurations
Quick test
badgr serve openbmb/MiniCPM5-2B --max-cost 2Validated dedicated endpoint command
badgr serve openbmb/MiniCPM5-2B --gpu RTX 4090 --max-cost 10Advanced configuration (defaults to automatic)
- Runtime
- Quantisation
- GPU and GPU count
- Context length
- Maximum concurrency
- Region
- Maximum hourly spend
- Persistent or capped runtime
Estimated pricing
Provider estimate: cold start
2–5 min
Provider estimate: endpoint cost
$0.19 – $0.50/hr
Idle cost
$0 when stopped
Per-token throughput cost is not shown here: Badgr has not benchmarked this model yet, and this page does not display figures it cannot back with real data.
Recommended Badgr routes
RTX 4090 24GB · United States
Availablefrom $0.19/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · United States
Availablefrom $0.44/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
RTX 4090 24GB · United States
Availablefrom $0.50/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
Known limitations
- Memory use increases with context length and concurrency.