# NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Ornith-1.5-122B (slim)

> NVIDIA Nemotron 3.5 Bolt E4B 4GB and Ornith-1.5-122B 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/nemotron-3-5-bolt-e4b-4gb-vs-ornith-1-5-122b.md (~10,250 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-ornith-1-5-122b.json · canonical https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-ornith-1-5-122b
- 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)

NVIDIA Nemotron 3.5 Bolt E4B 4GB and Ornith-1.5-122B score within a point of each other on agent readiness, 61 (C) and 61 (C). Both do open-weight models you run yourself.

- NVIDIA Nemotron 3.5 Bolt E4B 4GB: C 61, rank #49 of 160 open-weight models · https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb.min.md
- Ornith-1.5-122B: C 61, rank #81 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-122b.min.md
- NVIDIA Nemotron 3.5 Bolt E4B 4GB, good for Agents and apps that need a fast local conversational model with tool calls on an 8 to 12 GB GPU, a Mac or a Jetson, such as voice assistants and game characters. Ahead on Reach, 90 against 75; Risk, 80 against 50; Documentation and upkeep, 65 against 36.
- Ornith-1.5-122B, good for Local coding and terminal agents on a 128 GB unified-memory machine or a 96 GB GPU setup, where a clear licence file and an answering publisher aren't required

| Category | NVIDIA Nemotron 3.5 Bolt E4B 4GB | Ornith-1.5-122B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 75 |
| Risk (20%) | 80 | 50 |
| Agent interface (10%) | 85 | 85 |
| Documentation and upkeep (10%) | 65 | 36 |

| Fact (where they differ) | NVIDIA Nemotron 3.5 Bolt E4B 4GB | Ornith-1.5-122B |
| --- | --- | --- |
| Vendor | NVIDIA | Ornith |
| Licence | OpenMDW-1.1 | MIT |
| Last release | 2026-10-23 | 2026-10-24 |
| Agent reviews | 4/5 (4) | none |

Why the edge:
- Risk, NVIDIA Nemotron 3.5 Bolt E4B 4GB +30: NVIDIA Nemotron 3.5 Bolt E4B 4GB 80 (File safety earns 25, safetensors and GGUF only, and the documented routes run no repository code (an undocumented Inference Endpoints handler.py sits in the BF…); Ornith-1.5-122B 50 (File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from…)
- Documentation and upkeep, NVIDIA Nemotron 3.5 Bolt E4B 4GB +29: NVIDIA Nemotron 3.5 Bolt E4B 4GB 65 (The model card earns 20, all seven items with limitations in the linked subcard.); Ornith-1.5-122B 36 (Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.)
- Reach, NVIDIA Nemotron 3.5 Bolt E4B 4GB +15: NVIDIA Nemotron 3.5 Bolt E4B 4GB 90 (Memory earns 30, since NVIDIA's Q4_K_M GGUF is 6.18 GB, 7.4 GB with a fifth added.); Ornith-1.5-122B 75 (Memory 10, since Ornith's own MLX 4-bit build is 69.7 GB and needs about 83.6 GB with the fifth added, over 64 GB and inside the reference machine's 107.4 GB, a…)