Head to head · Open-weight models you run yourself · October 2026 research run
Laguna M.1 vs MiniCPM-o 4.5
MiniCPM-o 4.5 scores 61 (C) on agent readiness against Laguna M.1's 55.5 (C), and leads in 2 of 4 scored categories. Laguna M.1 leads on risk and agent interface. 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
Laguna M.1Poolside · Open-weight model
C55.5/100#79 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 Teams with a multi-GPU Blackwell or Hopper server that want a large coding agent model under Apache 2.0.
Ahead on
- Risk, 55 against 40
- Agent interface, 85 against 35
Watch for
The smallest build needs about 167 GB, more than a 128 GB machine
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
- Reach, 90 against 65
- Documentation and upkeep, 66 against 36
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 | Laguna M.1 | MiniCPM-o 4.5 | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 65 | 90 | MiniCPM-o 4.5 +25 |
| Risk | 20%20 | 55 | 40 | Laguna M.1 +15 |
| Agent interface | 10%10 | 85 | 35 | Laguna M.1 +50 |
| Documentation and upkeep | 10%10 | 36 | 66 | MiniCPM-o 4.5 +30 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 55.5/100 | C 61/100 |
Facts side by side
| Fact | Laguna M.1 | MiniCPM-o 4.5 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Poolside | 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 | |
| Privacy policy last updated | 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 | 2.5/5 (4) | 2.8/5 (4) |
Verdicts
Laguna M.1
A large coding and agent cousin under plain Apache 2.0, for agents with a multi-GPU server. Its smallest build needs about 167 GB, more than a 128 GB machine, and no local runtime library packages it. The main risks are no upkeep since July, no hosted fallback shown today, no safety results, and repository code on the SGLang route.
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
Laguna M.1
- Run the NVFP4 build on Blackwell GPUs with
vllm serve poolside/Laguna-M.1-NVFP4 --tensor-parallel-size 2 --tool-call-parser poolside_v1 --reasoning-parser poolside_v1 --enable-auto-tool-choice, on vLLM 0.21.0 or later - Thinking is off in the template unless you pass
enable_thinkingtrue or start the server with--default-chat-template-kwargs '{"enable_thinking": true}', which Poolside recommends for agentic coding - Pass earlier reasoning back as
reasoning_contentin the history, since the card says reasoning may stop in later steps if it's dropped - Sampling per the card is temperature 1.0 and top_k 20
- The FP8 build's Docker image and serve.sh predate upstream support and set a 4,096-token context, so prefer a released vLLM
- It doesn't fit our 128 GB reference machine at any published precision
- Validate JSON output yourself or use the runtime's guided decoding, 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, Laguna M.1 or MiniCPM-o 4.5?
MiniCPM-o 4.5 scores 61 (C) on agent readiness against Laguna M.1's 55.5 (C), and leads in 2 of 4 scored categories. Laguna M.1 leads on risk and agent interface.
Other comparisons with Laguna M.1 or MiniCPM-o 4.5
- Agents-A1-4B vs Laguna M.1
- Agents-A1-4B vs MiniCPM-o 4.5
- Apertus v1.5 8B vs Laguna M.1
- Apertus v1.5 8B vs MiniCPM-o 4.5
- Apodex-1.1-mini vs Laguna M.1
- Apodex-1.1-mini vs MiniCPM-o 4.5
- BigBang-v1 vs Laguna M.1
- BigBang-v1 vs MiniCPM-o 4.5
- Cosmos-Reason2-2B vs Laguna M.1
- Cosmos-Reason2-2B vs MiniCPM-o 4.5
- Darwin-36B-Opus vs Laguna M.1
- Darwin-36B-Opus vs MiniCPM-o 4.5
- DeepSeek-V3.2 vs Laguna M.1
- DeepSeek-V3.2 vs MiniCPM-o 4.5
- DeepSeek V4.1 Flash vs Laguna M.1
- DeepSeek V4.1 Flash vs MiniCPM-o 4.5
- DeepSeek-V4-Flash-0731 vs Laguna M.1
- DeepSeek-V4-Flash-0731 vs MiniCPM-o 4.5
- DiffusionGemma 26B A4B IT vs Laguna M.1
- DiffusionGemma 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 12B IT vs Laguna M.1
- Gemma 4 12B IT vs MiniCPM-o 4.5
- Gemma 4 26B A4B IT vs Laguna M.1
- Gemma 4 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 31B IT vs Laguna M.1
- Gemma 4 31B IT vs MiniCPM-o 4.5
- Gemma 4 E2B IT vs Laguna M.1
- Gemma 4 E2B IT vs MiniCPM-o 4.5
- Gemma 4 E4B IT vs Laguna M.1
- Gemma 4 E4B IT vs MiniCPM-o 4.5
- GLM-4.5-Air vs Laguna M.1
- GLM-4.5-Air vs MiniCPM-o 4.5
- GLM-4.7-Flash vs Laguna M.1
- GLM-4.7-Flash vs MiniCPM-o 4.5
- GLM-5.3-Flash vs Laguna M.1
- GLM-5.3-Flash vs MiniCPM-o 4.5
- GLM-5.3 vs Laguna M.1
- GLM-5.3 vs MiniCPM-o 4.5
- gpt-oss-120b vs Laguna M.1
- gpt-oss-120b vs MiniCPM-o 4.5
- gpt-oss-20b vs Laguna M.1
- gpt-oss-20b vs MiniCPM-o 4.5
- Granite 4.2 3B vs Laguna M.1
- Granite 4.2 3B vs MiniCPM-o 4.5
- Hy3 vs Laguna M.1
- Hy3 vs MiniCPM-o 4.5
- Inkling-Small vs Laguna M.1
- Inkling-Small vs MiniCPM-o 4.5
- Inkling vs Laguna M.1
- Inkling vs MiniCPM-o 4.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Laguna M.1
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM-o 4.5
- Kimi K3 vs Laguna M.1
- Kimi K3 vs MiniCPM-o 4.5
- Kolibri-1 vs Laguna M.1
- Kolibri-1 vs MiniCPM-o 4.5
- Laguna M.1 vs Laguna S 2.1
- Laguna M.1 vs Laguna XS 2.1
- Laguna M.1 vs LFM2.5-2.6B
- Laguna M.1 vs Ling-3.0-tiny
- Laguna M.1 vs MiMo-V2.6 Distill Qwen 9B
- Laguna M.1 vs MiniCPM5-2B
- Laguna M.1 vs MiniMax-M2.5
- Laguna M.1 vs MiniMax-M2.7
- Laguna M.1 vs Muse Glimmer 30B
- Laguna M.1 vs Nemotron 3.5 Lightning 30B A3B
- Laguna M.1 vs Nemotron 3 Nano 30B A3B
- Laguna M.1 vs Nemotron 3 Nano 4B
- Laguna M.1 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Laguna M.1 vs Nemotron 3 Super 120B A12B
- Laguna M.1 vs Nemotron 3 Ultra 550B A55B
- Laguna M.1 vs occamy-1.0
- Laguna M.1 vs Olmo 3 7B Think
- Laguna M.1 vs Ornith-1.5-35B-A3B
- Laguna M.1 vs Ornith-1.5-397B
- Laguna M.1 vs Ornith-1.5-9B
- Laguna M.1 vs Qwen3-30B-A3B-Instruct-2507
- Laguna M.1 vs Qwen3-4B-Instruct-2507
- Laguna M.1 vs Qwen3.5-0.8B
- Laguna M.1 vs Qwen3.5-122B-A10B
- Laguna M.1 vs Qwen3.5-2B
- Laguna M.1 vs Qwen3.5-397B-A17B
- Laguna M.1 vs Qwen3.5-4B
- Laguna M.1 vs Qwen3.5-9B
- Laguna M.1 vs Qwen3.6-27B
- Laguna M.1 vs Qwen3.6-35B-A3B
- Laguna M.1 vs Qwen3.8-27B
- Laguna M.1 vs Qwen3.8-Flash-Next
- Laguna M.1 vs Qwen3-Coder-30B-A3B-Instruct
- Laguna M.1 vs Qwen3-Coder-Next
- Laguna M.1 vs Qwen3-Omni-30B-A3B-Instruct
- Laguna M.1 vs Qwen3-VL-2B-Instruct
- Laguna M.1 vs Qwen3-VL-30B-A3B-Instruct
- Laguna M.1 vs Qwen3-VL-32B-Instruct
- Laguna M.1 vs Qwen3-VL-4B-Instruct
- Laguna M.1 vs Qwen3-VL-8B-Instruct
- Laguna M.1 vs Qwopus3.8-27B-Flash-V2
- Laguna M.1 vs SmolLM3-3B
- Laguna M.1 vs Spark-X2.6-4B
- Laguna M.1 vs Swift 1.5 Qwen3.8-27B
- Laguna M.1 vs Swift 1.5 Qwen3.8-Flash-Next
- Laguna M.1 vs ThinkingCap (Qwen3.8 27B)
- 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/laguna-m-1-vs-minicpm-o-4-5.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/laguna-m-1.json·/api/v1/tools/minicpm-o-4-5.json - From a terminal
anchor compare laguna-m-1 minicpm-o-4-5(the CLI) - Over MCP
compare_tools {"a": "laguna-m-1", "b": "minicpm-o-4-5"}at/mcp, no key