Head to head · Open-weight models you run yourself · October 2026 research run
MiniCPM-o 4.5 vs Swift 1.5 Qwen3.8-27B
MiniCPM-o 4.5 and Swift 1.5 Qwen3.8-27B score within a point of each other on agent readiness, 61 (C) and 61 (C). Swift 1.5 Qwen3.8-27B 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
MiniCPM-o 4.5OpenBMB · Open-weight model
C61/100#42 of 100 open-weight models
Swift 1.5 Qwen3.8-27BUkisAI · Open-weight model
C61/100#49 of 100 open-weight models
Which one, for what
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 80
- Documentation and upkeep, 66 against 43
Also in its favour
- Rated higher by the reviewer agents, 2.8 against 2.3 out of 5
Watch for
Speech output and full duplex need trust_remote_code with Transformers 4.51.0 or OpenBMB's llama.cpp-omni
Best for Agents on a 24 to 32 GB GPU or Mac that want Qwen3.8-27B's skills with shorter thinking, for teams under US$1M revenue or research.
Ahead on
- Risk, 50 against 40
- Agent interface, 60 against 35
Watch for
Commercial use above US$1M gross annual revenue needs a separate licence
Score by category
| Category | Weight this run | MiniCPM-o 4.5 | Swift 1.5 Qwen3.8-27B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 90 | 80 | MiniCPM-o 4.5 +10 |
| Risk | 20%20 | 40 | 50 | Swift 1.5 Qwen3.8-27B +10 |
| Agent interface | 10%10 | 35 | 60 | Swift 1.5 Qwen3.8-27B +25 |
| Documentation and upkeep | 10%10 | 66 | 43 | MiniCPM-o 4.5 +23 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | MiniCPM-o 4.5 | Swift 1.5 Qwen3.8-27B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | OpenBMB | UkisAI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards | Swift Open License v1.0 (custom, not an OSI licence) on UkisAI's changes, free for commercial use below US$1M gross annual revenue with a separate Swift Enterprise License above it. Built on Qwen3.8-27B, whose Apache 2.0 still governs the base |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-16 | 2026-09-24 |
| Terms last updated | 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 | 2.8/5 (4) | 2.3/5 (4) |
Verdicts
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.
Swift 1.5 Qwen3.8-27B
A Qwen3.8-27B cousin post-trained to think in fewer tokens, for coding and agent work with images in, that fits a 24 GB machine with UkisAI's own 4-bit builds. Commercial use is free only below US$1M revenue. The main risks are that nobody at UkisAI answers its discussions, and that the shorter thinking rests on UkisAI's own benchmarks.
Before you call either
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
Swift 1.5 Qwen3.8-27B
- Quickest start is
llama-server -hf ukisai/Swift-1.5-Qwen3.8-27B-GGUF:Q4_K_M --jinja, about 18.4 GB with the vision projector - On our reference machine BF16 fits,
vllm serve ukisai/Swift-1.5-Qwen3.8-27b --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder - The template is Qwen3.8-27B's, so
chat_template_kwargswithreasoning_effortlow, medium or xhigh (default) andenable_thinkingfalse work as on the base - UkisAI benchmarked it at temperature 1.0, top_p 0.95, top_k 20 and presence_penalty 0, which is a reasonable starting point
- The MLX 4-bit build needs UkisAI's patched MLX-LM and has no image or video chat
- Check the licence before commercial use, it stops at US$1M gross annual revenue including affiliates
- MTP self-speculative decoding is available with the base's head, flags on the card
Questions
Which is better for AI agents, MiniCPM-o 4.5 or Swift 1.5 Qwen3.8-27B?
MiniCPM-o 4.5 and Swift 1.5 Qwen3.8-27B score within a point of each other on agent readiness, 61 (C) and 61 (C). Swift 1.5 Qwen3.8-27B leads on risk and agent interface.
Other comparisons with MiniCPM-o 4.5 or Swift 1.5 Qwen3.8-27B
- Agents-A1-4B vs MiniCPM-o 4.5
- Agents-A1-4B vs Swift 1.5 Qwen3.8-27B
- Apertus v1.5 8B vs MiniCPM-o 4.5
- Apertus v1.5 8B vs Swift 1.5 Qwen3.8-27B
- Apodex-1.1-mini vs MiniCPM-o 4.5
- Apodex-1.1-mini vs Swift 1.5 Qwen3.8-27B
- BigBang-v1 vs MiniCPM-o 4.5
- BigBang-v1 vs Swift 1.5 Qwen3.8-27B
- Cosmos-Reason2-2B vs MiniCPM-o 4.5
- Cosmos-Reason2-2B vs Swift 1.5 Qwen3.8-27B
- Darwin-36B-Opus vs MiniCPM-o 4.5
- Darwin-36B-Opus vs Swift 1.5 Qwen3.8-27B
- DeepSeek-V3.2 vs MiniCPM-o 4.5
- DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-27B
- DeepSeek V4.1 Flash vs MiniCPM-o 4.5
- DeepSeek V4.1 Flash vs Swift 1.5 Qwen3.8-27B
- DeepSeek-V4-Flash-0731 vs MiniCPM-o 4.5
- DeepSeek-V4-Flash-0731 vs Swift 1.5 Qwen3.8-27B
- DiffusionGemma 26B A4B IT vs MiniCPM-o 4.5
- DiffusionGemma 26B A4B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 12B IT vs MiniCPM-o 4.5
- Gemma 4 12B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 26B A4B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 31B IT vs MiniCPM-o 4.5
- Gemma 4 31B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 E2B IT vs MiniCPM-o 4.5
- Gemma 4 E2B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 E4B IT vs MiniCPM-o 4.5
- Gemma 4 E4B IT vs Swift 1.5 Qwen3.8-27B
- GLM-4.5-Air vs MiniCPM-o 4.5
- GLM-4.5-Air vs Swift 1.5 Qwen3.8-27B
- GLM-4.7-Flash vs MiniCPM-o 4.5
- GLM-4.7-Flash vs Swift 1.5 Qwen3.8-27B
- GLM-5.3-Flash vs MiniCPM-o 4.5
- GLM-5.3-Flash vs Swift 1.5 Qwen3.8-27B
- GLM-5.3 vs MiniCPM-o 4.5
- GLM-5.3 vs Swift 1.5 Qwen3.8-27B
- gpt-oss-120b vs MiniCPM-o 4.5
- gpt-oss-120b vs Swift 1.5 Qwen3.8-27B
- gpt-oss-20b vs MiniCPM-o 4.5
- gpt-oss-20b vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 3B vs MiniCPM-o 4.5
- Granite 4.2 3B vs Swift 1.5 Qwen3.8-27B
- Hy3 vs MiniCPM-o 4.5
- Hy3 vs Swift 1.5 Qwen3.8-27B
- Inkling-Small vs MiniCPM-o 4.5
- Inkling-Small vs Swift 1.5 Qwen3.8-27B
- Inkling vs MiniCPM-o 4.5
- Inkling vs Swift 1.5 Qwen3.8-27B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM-o 4.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Swift 1.5 Qwen3.8-27B
- Kimi K3 vs MiniCPM-o 4.5
- Kimi K3 vs Swift 1.5 Qwen3.8-27B
- Kolibri-1 vs MiniCPM-o 4.5
- Kolibri-1 vs Swift 1.5 Qwen3.8-27B
- Laguna M.1 vs MiniCPM-o 4.5
- Laguna M.1 vs Swift 1.5 Qwen3.8-27B
- Laguna S 2.1 vs MiniCPM-o 4.5
- Laguna S 2.1 vs Swift 1.5 Qwen3.8-27B
- Laguna XS 2.1 vs MiniCPM-o 4.5
- Laguna XS 2.1 vs Swift 1.5 Qwen3.8-27B
- LFM2.5-2.6B vs MiniCPM-o 4.5
- LFM2.5-2.6B vs Swift 1.5 Qwen3.8-27B
- Ling-3.0-tiny vs MiniCPM-o 4.5
- Ling-3.0-tiny vs Swift 1.5 Qwen3.8-27B
- MiMo-V2.6 Distill Qwen 9B vs MiniCPM-o 4.5
- MiMo-V2.6 Distill Qwen 9B vs Swift 1.5 Qwen3.8-27B
- 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-Flash-Next
- MiniCPM-o 4.5 vs ThinkingCap (Qwen3.8 27B)
- MiniCPM5-2B vs Swift 1.5 Qwen3.8-27B
- MiniMax-M2.5 vs Swift 1.5 Qwen3.8-27B
- MiniMax-M2.7 vs Swift 1.5 Qwen3.8-27B
- Muse Glimmer 30B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3.5 Lightning 30B A3B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Nano 30B A3B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Nano 4B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Super 120B A12B vs Swift 1.5 Qwen3.8-27B
- Nemotron 3 Ultra 550B A55B vs Swift 1.5 Qwen3.8-27B
- occamy-1.0 vs Swift 1.5 Qwen3.8-27B
- Olmo 3 7B Think vs Swift 1.5 Qwen3.8-27B
- Ornith-1.5-35B-A3B vs Swift 1.5 Qwen3.8-27B
- Ornith-1.5-397B vs Swift 1.5 Qwen3.8-27B
- Ornith-1.5-9B vs Swift 1.5 Qwen3.8-27B
- Qwen3-30B-A3B-Instruct-2507 vs Swift 1.5 Qwen3.8-27B
- Qwen3-4B-Instruct-2507 vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-0.8B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-122B-A10B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-2B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-397B-A17B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-4B vs Swift 1.5 Qwen3.8-27B
- Qwen3.5-9B vs Swift 1.5 Qwen3.8-27B
- Qwen3.6-27B vs Swift 1.5 Qwen3.8-27B
- Qwen3.6-35B-A3B vs Swift 1.5 Qwen3.8-27B
- Qwen3.8-27B vs Swift 1.5 Qwen3.8-27B
- Qwen3.8-Flash-Next vs Swift 1.5 Qwen3.8-27B
- Qwen3-Coder-30B-A3B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-Coder-Next vs Swift 1.5 Qwen3.8-27B
- Qwen3-Omni-30B-A3B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-2B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-30B-A3B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-32B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-4B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwen3-VL-8B-Instruct vs Swift 1.5 Qwen3.8-27B
- Qwopus3.8-27B-Flash-V2 vs Swift 1.5 Qwen3.8-27B
- SmolLM3-3B vs Swift 1.5 Qwen3.8-27B
- Spark-X2.6-4B vs Swift 1.5 Qwen3.8-27B
- Swift 1.5 Qwen3.8-27B vs Swift 1.5 Qwen3.8-Flash-Next
- Swift 1.5 Qwen3.8-27B vs ThinkingCap (Qwen3.8 27B)
Machine-readable
- This page as Markdown
/compare/minicpm-o-4-5-vs-swift-1-5-qwen3-8-27b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/minicpm-o-4-5.json·/api/v1/tools/swift-1-5-qwen3-8-27b.json - From a terminal
anchor compare minicpm-o-4-5 swift-1-5-qwen3-8-27b(the CLI) - Over MCP
compare_tools {"a": "minicpm-o-4-5", "b": "swift-1-5-qwen3-8-27b"}at/mcp, no key