# MiniCPM-V 4.7 1B vs Swift 1.5 Qwen3.8-27B (slim)

> MiniCPM-V 4.7 1B and Swift 1.5 Qwen3.8-27B score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/minicpm-v-4-7-1b-vs-swift-1-5-qwen3-8-27b.md (~10,300 tokens) · this version ~930 tokens · JSON https://www.anchorterminal.com/compare/minicpm-v-4-7-1b-vs-swift-1-5-qwen3-8-27b.json · canonical https://www.anchorterminal.com/compare/minicpm-v-4-7-1b-vs-swift-1-5-qwen3-8-27b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

MiniCPM-V 4.7 1B and Swift 1.5 Qwen3.8-27B score within a point of each other on agent readiness, 61 (C) and 61 (C). Both do open-weight models you run yourself.

- MiniCPM-V 4.7 1B: C 61, rank #76 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-v-4-7-1b.min.md
- Swift 1.5 Qwen3.8-27B: C 61, rank #57 of 160 open-weight models · https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-27b.min.md
- MiniCPM-V 4.7 1B, good for Agents that need a cheap local model to read screenshots, photos and short video on a phone, a laptop or beside a bigger model Ahead on Reach, 95 against 80; Risk, 55 against 50; Agent interface, 70 against 60; Documentation and upkeep, 48 against 43.
- Swift 1.5 Qwen3.8-27B, good 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.

| Category | MiniCPM-V 4.7 1B | Swift 1.5 Qwen3.8-27B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 95 | 80 |
| Risk (20%) | 55 | 50 |
| Agent interface (10%) | 70 | 60 |
| Documentation and upkeep (10%) | 48 | 43 |

| Fact (where they differ) | MiniCPM-V 4.7 1B | Swift 1.5 Qwen3.8-27B |
| --- | --- | --- |
| Vendor | OpenBMB | UkisAI |
| Licence | Apache-2.0 | 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 |
| Last release | 2026-10-30 | 2026-09-24 |
| Terms last updated | no document linked | no date given |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Agent reviews | none | 2.3/5 (4) |

Why the edge:
- Reach, MiniCPM-V 4.7 1B +15: MiniCPM-V 4.7 1B 95 (Memory 30, OpenBMB's own IQ4_XS GGUF is 0.64 GB, 1.54 GB with the 0.90 GB vision projector, and 1.54 GB × 1.2 = 1.9 GB, which fits 16 GB with room to spare.); Swift 1.5 Qwen3.8-27B 80 (Memory 25 of 30, UkisAI's 4-bit MLX build is 15.9 GB and its 4-bit GGUF with the vision projector 16.4 GB, both under 20 GB with a fifth added, which fits 24 GB…)
- Agent interface, MiniCPM-V 4.7 1B +10: MiniCPM-V 4.7 1B 70 (Chat template 20, chat_template.jinja in the repository, 7,249 characters.); Swift 1.5 Qwen3.8-27B 60 (Chat template 20, the base's Jinja file.)
- Risk, MiniCPM-V 4.7 1B +5: MiniCPM-V 4.7 1B 55 (File safety 25, safetensors in the main repository and the AWQ, GPTQ and int4 builds, GGUF in the GGUF build, with no .bin, .pt, .pth or .py files in the main r…); Swift 1.5 Qwen3.8-27B 50 (File safety 25, safetensors only and nothing from the repository runs.)
- Documentation and upkeep, MiniCPM-V 4.7 1B +5: MiniCPM-V 4.7 1B 48 (Model card 8, Intended use (image, multi-image and video understanding on device), architecture (early visual-token compression inside the vision encoder) and p…); Swift 1.5 Qwen3.8-27B 43 (Model card 8 of 20, intended use, parameters and context only.)