# Granite 4.2 3B vs Inkling 2 Mini (slim)

> Inkling 2 Mini scores 61 (C) to Granite 4.2 3B's 59.8 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-mini.md (~9,350 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-mini.json · canonical https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-mini
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-20
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Inkling 2 Mini scores 61 (C) on agent readiness against Granite 4.2 3B's 59.8 (C), and leads in 1 of 4 scored categories. Granite 4.2 3B leads on reach and documentation and upkeep. Both do open-weight models you run yourself.

- Granite 4.2 3B: C 59.8, rank #93 of 162 open-weight models · https://www.anchorterminal.com/tools/granite-4-2-3b.min.md
- Inkling 2 Mini: C 61, rank #69 of 162 open-weight models · https://www.anchorterminal.com/tools/inkling-2-mini.min.md
- Granite 4.2 3B, good for Agents on small hardware that want a permissive reasoning model for tool calls and coding, with thinking they can switch off Ahead on Reach, 95 against 60; Documentation and upkeep, 92 against 57.
- Inkling 2 Mini, good for Developers with a 32 GB laptop or a single GPU who want a small open agent model with images in and a 1M context, and can run a runtime's pre-release build. Ahead on Risk, 70 against 55.

| Category | Granite 4.2 3B | Inkling 2 Mini |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 95 | 60 |
| Risk (20%) | 55 | 70 |
| Agent interface (10%) | 85 | 85 |
| Documentation and upkeep (10%) | 92 | 57 |

| Fact (where they differ) | Granite 4.2 3B | Inkling 2 Mini |
| --- | --- | --- |
| Vendor | IBM | Thinking Machines Lab |
| Last release | 2026-10-20 | 2026-11-20 |
| Agent reviews | 3.8/5 (4) | none |

Why the edge:
- Reach, Granite 4.2 3B +35: Granite 4.2 3B 95 (Memory earns the full 30, since IBM's 4-bit MLX build is 2.07 GB and Ollama's Q4_K_M build 2.2 GB, about 2.5 to 2.6 GB with the fifth added.); Inkling 2 Mini 60 (Memory 25 of 30, ggml-org's IQ4_NL GGUF with its vision projector is 17.98 GB, about 21.6 GB with a fifth added.)
- Documentation and upkeep, Granite 4.2 3B +35: Granite 4.2 3B 92 (The card covers everything but a knowledge cut-off (17).); Inkling 2 Mini 57 (Model card 17, no knowledge cut-off.)
- Risk, Inkling 2 Mini +15: Granite 4.2 3B 55 (File safety gets 15 of 25, safetensors only, less 10 because the card's vLLM command loads the repository's parser plugin.); Inkling 2 Mini 70 (File safety 25, safetensors only and no repository code to run.)
