Head to head · Open-weight models you run yourself · October 2026 research run
Agents-A1-4B vs MiniCPM-o 4.5
Agents-A1-4B and MiniCPM-o 4.5 score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-o 4.5 leads on documentation and upkeep. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 2870 open weights comparisons
Best conversational voice-agent APIs · All 388 voice agents comparisons
Agents-A1-4BInternScience (Shanghai AI Laboratory) · Open-weight model
C61/100#34 of 100 open-weight models
MiniCPM-o 4.5OpenBMB · Open-weight model
C61/100#42 of 100 open-weight models
Which one, for what
Best for Local agent loops (search, research, tool calls) on a laptop, a small GPU or a phone-class machine, under a plain licence
Ahead on
- Risk, 55 against 40
- Agent interface, 70 against 35
Watch for
The base isn't declared, and the technical report doesn't cover the 4B
Best for Agents that need a local model to see, hear and speak on a laptop or a single small GPU, with a plain licence.
Ahead on
- Documentation and upkeep, 66 against 43
Watch for
Speech output and full duplex need trust_remote_code with Transformers 4.51.0 or OpenBMB's llama.cpp-omni
Score by category
| Category | Weight this run | Agents-A1-4B | MiniCPM-o 4.5 | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 90 | 90 | even |
| Risk | 20%20 | 55 | 40 | Agents-A1-4B +15 |
| Agent interface | 10%10 | 70 | 35 | Agents-A1-4B +35 |
| Documentation and upkeep | 10%10 | 43 | 66 | MiniCPM-o 4.5 +23 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | Agents-A1-4B | MiniCPM-o 4.5 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | InternScience (Shanghai AI Laboratory) | OpenBMB |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-07-14 | 2026-10-16 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | 3/5 (4) | 2.8/5 (4) |
Verdicts
Agents-A1-4B
A small agent cousin for search, research and tool-calling loops, with vision and 262,144 tokens of context. It runs in about 4 GB from InternScience's Q4_K_M GGUF, in vLLM, SGLang, Transformers or llama.cpp. The main risks are an undeclared base, no safety results or agent guidance, and a template that adds its own dated system prompt when you send none.
MiniCPM-o 4.5
A small omni cousin that sees, listens and talks back, with full-duplex speech and voice cloning, in about 7 GB at 4-bit through llama.cpp or Ollama for text and images. Speech output needs OpenBMB's remote code or llama.cpp-omni, and 28 GB of GPU for the full demo. The main risks are repository code and pickle files and no safety results.
Before you call either
Agents-A1-4B
- Quickest start is
llama-server -hf InternScience/Agents-A1-4B-Q4_K_M-GGUF --jinja, about 3.4 GB with the vision projector - With vLLM use
--reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder, as on the card, and add--language-model-onlyfor text-only work - Always send your own system message, or the template inserts InternScience's default prompt with the date fixed at 2026-07-14
- The card recommends temperature 0.85, top_p 0.95, top_k 20, min_p 0 and presence_penalty 1.1, and there is no generation_config.json to set them
- Thinking is on by default, send
chat_template_kwargswithenable_thinkingfalse for short tasks, a switch the card doesn't mention - The config declares a multi-token prediction layer that isn't shipped, so don't turn on MTP speculative decoding
- Validate JSON output yourself, since structured output isn't documented
MiniCPM-o 4.5
- Quickest start for text and images is
ollama run openbmb/minicpm-o4.5, about 6 GB - With vLLM 0.16.0 or later pass
--trust-remote-code, and sendstop_token_ids[151643, 151645] as OpenBMB's guide does - vLLM, llama.cpp and Ollama return text only; for speech out use the card's Transformers 4.51.0 code or OpenBMB's llama.cpp-omni
- In llama.cpp pass both the language GGUF and MiniCPM-o-4_5-vision-F16.gguf with
--mmproj, and use--jinja --reasoning-budget 0to turn thinking off - Keep prompts within 40,960 tokens
- Don't rely on tool calls or JSON output, neither is documented; validate any you get
Questions
Which is better for AI agents, Agents-A1-4B or MiniCPM-o 4.5?
Agents-A1-4B and MiniCPM-o 4.5 score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-o 4.5 leads on documentation and upkeep.
Other comparisons with Agents-A1-4B or MiniCPM-o 4.5
- Agents-A1-4B vs Apertus v1.5 8B
- Agents-A1-4B vs Apodex-1.1-mini
- Agents-A1-4B vs BigBang-v1
- Agents-A1-4B vs Cosmos-Reason2-2B
- Agents-A1-4B vs Darwin-36B-Opus
- Agents-A1-4B vs DeepSeek-V3.2
- Agents-A1-4B vs DeepSeek V4.1 Flash
- Agents-A1-4B vs DeepSeek-V4-Flash-0731
- Agents-A1-4B vs DiffusionGemma 26B A4B IT
- Agents-A1-4B vs Gemma 4 12B IT
- Agents-A1-4B vs Gemma 4 26B A4B IT
- Agents-A1-4B vs Gemma 4 31B IT
- Agents-A1-4B vs Gemma 4 E2B IT
- Agents-A1-4B vs Gemma 4 E4B IT
- Agents-A1-4B vs GLM-4.5-Air
- Agents-A1-4B vs GLM-4.7-Flash
- Agents-A1-4B vs GLM-5.3
- Agents-A1-4B vs GLM-5.3-Flash
- Agents-A1-4B vs gpt-oss-120b
- Agents-A1-4B vs gpt-oss-20b
- Agents-A1-4B vs Granite 4.2 3B
- Agents-A1-4B vs Hy3
- Agents-A1-4B vs Inkling
- Agents-A1-4B vs Inkling-Small
- Agents-A1-4B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Agents-A1-4B vs Kimi K3
- Agents-A1-4B vs Kolibri-1
- Agents-A1-4B vs Laguna M.1
- Agents-A1-4B vs Laguna S 2.1
- Agents-A1-4B vs Laguna XS 2.1
- Agents-A1-4B vs LFM2.5-2.6B
- Agents-A1-4B vs Ling-3.0-tiny
- Agents-A1-4B vs MiMo-V2.6 Distill Qwen 9B
- Agents-A1-4B vs MiniCPM5-2B
- Agents-A1-4B vs MiniMax-M2.5
- Agents-A1-4B vs MiniMax-M2.7
- Agents-A1-4B vs Muse Glimmer 30B
- Agents-A1-4B vs Nemotron 3.5 Lightning 30B A3B
- Agents-A1-4B vs Nemotron 3 Nano 30B A3B
- Agents-A1-4B vs Nemotron 3 Nano 4B
- Agents-A1-4B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Agents-A1-4B vs Nemotron 3 Super 120B A12B
- Agents-A1-4B vs Nemotron 3 Ultra 550B A55B
- Agents-A1-4B vs occamy-1.0
- Agents-A1-4B vs Olmo 3 7B Think
- Agents-A1-4B vs Ornith-1.5-35B-A3B
- Agents-A1-4B vs Ornith-1.5-397B
- Agents-A1-4B vs Ornith-1.5-9B
- Agents-A1-4B vs Qwen3-30B-A3B-Instruct-2507
- Agents-A1-4B vs Qwen3-4B-Instruct-2507
- Agents-A1-4B vs Qwen3.5-0.8B
- Agents-A1-4B vs Qwen3.5-122B-A10B
- Agents-A1-4B vs Qwen3.5-2B
- Agents-A1-4B vs Qwen3.5-397B-A17B
- Agents-A1-4B vs Qwen3.5-4B
- Agents-A1-4B vs Qwen3.5-9B
- Agents-A1-4B vs Qwen3.6-27B
- Agents-A1-4B vs Qwen3.6-35B-A3B
- Agents-A1-4B vs Qwen3.8-27B
- Agents-A1-4B vs Qwen3.8-Flash-Next
- Agents-A1-4B vs Qwen3-Coder-30B-A3B-Instruct
- Agents-A1-4B vs Qwen3-Coder-Next
- Agents-A1-4B vs Qwen3-Omni-30B-A3B-Instruct
- Agents-A1-4B vs Qwen3-VL-2B-Instruct
- Agents-A1-4B vs Qwen3-VL-30B-A3B-Instruct
- Agents-A1-4B vs Qwen3-VL-32B-Instruct
- Agents-A1-4B vs Qwen3-VL-4B-Instruct
- Agents-A1-4B vs Qwen3-VL-8B-Instruct
- Agents-A1-4B vs Qwopus3.8-27B-Flash-V2
- Agents-A1-4B vs SmolLM3-3B
- Agents-A1-4B vs Spark-X2.6-4B
- Agents-A1-4B vs Swift 1.5 Qwen3.8-27B
- Agents-A1-4B vs Swift 1.5 Qwen3.8-Flash-Next
- Agents-A1-4B vs ThinkingCap (Qwen3.8 27B)
- Apertus v1.5 8B vs MiniCPM-o 4.5
- Apodex-1.1-mini vs MiniCPM-o 4.5
- BigBang-v1 vs MiniCPM-o 4.5
- Cosmos-Reason2-2B vs MiniCPM-o 4.5
- Darwin-36B-Opus vs MiniCPM-o 4.5
- DeepSeek-V3.2 vs MiniCPM-o 4.5
- DeepSeek V4.1 Flash vs MiniCPM-o 4.5
- DeepSeek-V4-Flash-0731 vs MiniCPM-o 4.5
- DiffusionGemma 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 12B IT vs MiniCPM-o 4.5
- Gemma 4 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 31B IT vs MiniCPM-o 4.5
- Gemma 4 E2B IT vs MiniCPM-o 4.5
- Gemma 4 E4B IT vs MiniCPM-o 4.5
- GLM-4.5-Air vs MiniCPM-o 4.5
- GLM-4.7-Flash vs MiniCPM-o 4.5
- GLM-5.3-Flash vs MiniCPM-o 4.5
- GLM-5.3 vs MiniCPM-o 4.5
- gpt-oss-120b vs MiniCPM-o 4.5
- gpt-oss-20b vs MiniCPM-o 4.5
- Granite 4.2 3B vs MiniCPM-o 4.5
- Hy3 vs MiniCPM-o 4.5
- Inkling-Small vs MiniCPM-o 4.5
- Inkling vs MiniCPM-o 4.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM-o 4.5
- Kimi K3 vs MiniCPM-o 4.5
- Kolibri-1 vs MiniCPM-o 4.5
- Laguna M.1 vs MiniCPM-o 4.5
- Laguna S 2.1 vs MiniCPM-o 4.5
- Laguna XS 2.1 vs MiniCPM-o 4.5
- LFM2.5-2.6B vs MiniCPM-o 4.5
- Ling-3.0-tiny vs MiniCPM-o 4.5
- MiMo-V2.6 Distill Qwen 9B vs MiniCPM-o 4.5
- MiniCPM-o 4.5 vs MiniCPM5-2B
- MiniCPM-o 4.5 vs MiniMax-M2.5
- MiniCPM-o 4.5 vs MiniMax-M2.7
- MiniCPM-o 4.5 vs Muse Glimmer 30B
- MiniCPM-o 4.5 vs Nemotron 3.5 Lightning 30B A3B
- MiniCPM-o 4.5 vs Nemotron 3 Nano 30B A3B
- MiniCPM-o 4.5 vs Nemotron 3 Nano 4B
- MiniCPM-o 4.5 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- MiniCPM-o 4.5 vs Nemotron 3 Super 120B A12B
- MiniCPM-o 4.5 vs Nemotron 3 Ultra 550B A55B
- MiniCPM-o 4.5 vs occamy-1.0
- MiniCPM-o 4.5 vs Olmo 3 7B Think
- MiniCPM-o 4.5 vs Ornith-1.5-35B-A3B
- MiniCPM-o 4.5 vs Ornith-1.5-397B
- MiniCPM-o 4.5 vs Ornith-1.5-9B
- MiniCPM-o 4.5 vs Qwen3-30B-A3B-Instruct-2507
- MiniCPM-o 4.5 vs Qwen3-4B-Instruct-2507
- MiniCPM-o 4.5 vs Qwen3.5-0.8B
- MiniCPM-o 4.5 vs Qwen3.5-122B-A10B
- MiniCPM-o 4.5 vs Qwen3.5-2B
- MiniCPM-o 4.5 vs Qwen3.5-397B-A17B
- MiniCPM-o 4.5 vs Qwen3.5-4B
- MiniCPM-o 4.5 vs Qwen3.5-9B
- MiniCPM-o 4.5 vs Qwen3.6-27B
- MiniCPM-o 4.5 vs Qwen3.6-35B-A3B
- MiniCPM-o 4.5 vs Qwen3.8-27B
- MiniCPM-o 4.5 vs Qwen3.8-Flash-Next
- MiniCPM-o 4.5 vs Qwen3-Coder-30B-A3B-Instruct
- MiniCPM-o 4.5 vs Qwen3-Coder-Next
- MiniCPM-o 4.5 vs Qwen3-Omni-30B-A3B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-2B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-30B-A3B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-32B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-4B-Instruct
- MiniCPM-o 4.5 vs Qwen3-VL-8B-Instruct
- MiniCPM-o 4.5 vs Qwopus3.8-27B-Flash-V2
- MiniCPM-o 4.5 vs SmolLM3-3B
- MiniCPM-o 4.5 vs Spark-X2.6-4B
- MiniCPM-o 4.5 vs Swift 1.5 Qwen3.8-27B
- MiniCPM-o 4.5 vs Swift 1.5 Qwen3.8-Flash-Next
- MiniCPM-o 4.5 vs ThinkingCap (Qwen3.8 27B)
Machine-readable
- This page as Markdown
/compare/agents-a1-4b-vs-minicpm-o-4-5.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/agents-a1-4b.json·/api/v1/tools/minicpm-o-4-5.json - From a terminal
anchor compare agents-a1-4b minicpm-o-4-5(the CLI) - Over MCP
compare_tools {"a": "agents-a1-4b", "b": "minicpm-o-4-5"}at/mcp, no key