# Cosmos-Reason2-2B vs MiniCPM-V 4.7 1B (slim)

> MiniCPM-V 4.7 1B scores 61 (C) to Cosmos-Reason2-2B's 59.5 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-minicpm-v-4-7-1b.md (~10,150 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-minicpm-v-4-7-1b.json · canonical https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-minicpm-v-4-7-1b
- 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 scores 61 (C) on agent readiness against Cosmos-Reason2-2B's 59.5 (C), and leads in 3 of 4 scored categories. Cosmos-Reason2-2B leads on risk. Both do open-weight models you run yourself.

- Cosmos-Reason2-2B: C 59.5, rank #95 of 160 open-weight models · https://www.anchorterminal.com/tools/cosmos-reason2-2b.min.md
- 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
- Cosmos-Reason2-2B, good for Agents that need a small local model to reason over camera footage and images for robotics, driving or smart spaces Ahead on Risk, 60 against 55.
- 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 65; Agent interface, 70 against 65; Documentation and upkeep, 48 against 39.

| Category | Cosmos-Reason2-2B | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 95 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 70 |
| Documentation and upkeep (10%) | 39 | 48 |

| Fact (where they differ) | Cosmos-Reason2-2B | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Vendor | NVIDIA | OpenBMB |
| Licence | NVIDIA Open Model License (custom, commercial use allowed, not an OSI licence); built on Qwen3-VL-2B-Instruct under Apache 2.0 | Apache-2.0 |
| Last release | 2026-03-10 | 2026-10-30 |
| Terms last updated | 2025-10-24 | no document linked |
| Customer content may train models | yes | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Reach, MiniCPM-V 4.7 1B +30: Cosmos-Reason2-2B 65 (Memory earns the full 30 because the BF16 file is 4.9 GB, about 5.9 GB with the fifth added, though NVIDIA itself asks for 24 GB of GPU memory.); 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.)
- Documentation and upkeep, MiniCPM-V 4.7 1B +9: Cosmos-Reason2-2B 39 (The card misses languages and a cut-off (14).); 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…)
- Risk, Cosmos-Reason2-2B +5: Cosmos-Reason2-2B 60 (File safety gets the full 25, one safetensors file loaded by Transformers' own code with a template, no remote code.); 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…)
- Agent interface, MiniCPM-V 4.7 1B +5: Cosmos-Reason2-2B 65 (A Jinja template ships as chat_template.json (20).); MiniCPM-V 4.7 1B 70 (Chat template 20, chat_template.jinja in the repository, 7,249 characters.)