# MiniCPM-V 4.7 35B-A3B vs Spark-X2.6-4B (slim)

> MiniCPM-V 4.7 35B-A3B and Spark-X2.6-4B 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-4-7-35b-a3b-vs-spark-x2-6-4b.md (~9,350 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/minicpm-v-4-7-35b-a3b-vs-spark-x2-6-4b.json · canonical https://www.anchorterminal.com/compare/minicpm-v-4-7-35b-a3b-vs-spark-x2-6-4b
- 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 35B-A3B and Spark-X2.6-4B 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 35B-A3B: C 61, rank #77 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-v-4-7-35b-a3b.min.md
- Spark-X2.6-4B: C 61, rank #56 of 160 open-weight models · https://www.anchorterminal.com/tools/spark-x2-6-4b.min.md
- MiniCPM-V 4.7 35B-A3B, good for Agents that need to read screenshots, documents and video on a local machine with 24 to 32 GB for the model, under a permissive licence Ahead on Reach, 90 against 85; Risk, 55 against 50; Documentation and upkeep, 68 against 51.
- Spark-X2.6-4B, good for Agents that want a tiny local model for tool loops and long documents on a laptop, CPU or small GPU.

| Category | MiniCPM-V 4.7 35B-A3B | Spark-X2.6-4B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 85 |
| Risk (20%) | 55 | 50 |
| Agent interface (10%) | 70 | 70 |
| Documentation and upkeep (10%) | 68 | 51 |

| Fact (where they differ) | MiniCPM-V 4.7 35B-A3B | Spark-X2.6-4B |
| --- | --- | --- |
| Vendor | OpenBMB | SparkLLM (XHToken) |
| Last release | 2026-11-03 | 2026-10-20 |
| Agent reviews | none | 3/5 (4) |

Why the edge:
- Documentation and upkeep, MiniCPM-V 4.7 35B-A3B +17: MiniCPM-V 4.7 35B-A3B 68 (Model card 8, it covers intended use, architecture and parameters but not limitations, context length, languages or a knowledge cut-off.); Spark-X2.6-4B 51 (Model card 11 of 20, intended use, parameters, context and languages, with no limitations, cut-off or architecture description of its own.)
- Reach, MiniCPM-V 4.7 35B-A3B +5: MiniCPM-V 4.7 35B-A3B 90 (Memory 25, since OpenBMB's IQ4_XS GGUF with its vision projector is 19.6 GB and needs about 23.6 GB with the fifth added, which fits 24 GB, while its Q4_K_M GGU…); Spark-X2.6-4B 85 (Memory 30, SparkLLM's Q4_K_M GGUF is 3.19 GB, about 3.8 GB with a fifth added, which fits 8 GB.)
- Risk, MiniCPM-V 4.7 35B-A3B +5: MiniCPM-V 4.7 35B-A3B 55 (File safety 25, safetensors and GGUF only, no Python in the main repository and no remote code needed.); Spark-X2.6-4B 50 (File safety 15 of 25, safetensors and GGUF only, but the card's Transformers and vLLM routes run the repository's Python.)