# Granite Speech 5.0 2B vs Parakeet TDT 0.6B v3 (slim)

> Parakeet TDT 0.6B v3 scores 66.9 (B) to Granite Speech 5.0 2B's 61 (C) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-tdt-0-6b-v3.md (~4,150 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-tdt-0-6b-v3.json · canonical https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-parakeet-tdt-0-6b-v3
- 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)

Parakeet TDT 0.6B v3 scores 66.9 (B) on agent readiness against Granite Speech 5.0 2B's 61 (C), and leads in 0 of 4 scored categories. Granite Speech 5.0 2B leads on reach, risk, agent interface and documentation and upkeep. Both do speech-to-text.

- Granite Speech 5.0 2B: C 61, rank #67 of 160 open-weight models · https://www.anchorterminal.com/tools/granite-speech-5-0-2b.min.md
- Parakeet TDT 0.6B v3: B 66.9, rank #14 of 160 open-weight models · https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3.min.md
- Granite Speech 5.0 2B, good for Agents that need to transcribe or translate short recordings in the six supported languages on modest hardware Ahead on Reach, 95 against 65; Risk, 70 against 60; Agent interface, 55 against 50; Documentation and upkeep, 92 against 77.
- Parakeet TDT 0.6B v3, good for Agents that need cheap local transcription with timestamps in English and other European languages

| Category | Granite Speech 5.0 2B | Parakeet TDT 0.6B v3 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 95 | 65 |
| Risk (20%) | 70 | 60 |
| Agent interface (10%) | 55 | 50 |
| Documentation and upkeep (10%) | 92 | 77 |

| Fact (where they differ) | Granite Speech 5.0 2B | Parakeet TDT 0.6B v3 |
| --- | --- | --- |
| Vendor | IBM | NVIDIA |
| Licence | Apache-2.0 | CC-BY-4.0 |
| Last release | 2026-11-06 | 2026-08-05 |
| 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 | 4/5 (4) |

Why the edge:
- Reach, Granite Speech 5.0 2B +30: Granite Speech 5.0 2B 95 (Memory 30, the smallest build listed that keeps 4 bits is IBM's Q4_K_M GGUF, 1.14 GB with the 1.16 GB audio projector, and 2.30 GB × 1.2 = 2.8 GB, within 16 GB.); Parakeet TDT 0.6B v3 65 (Memory earns the full 30, NVIDIA's Q8_0 GGUF being 0.71 GB and even the FP32 files under 3 GB with the fifth added.)
- Documentation and upkeep, Granite Speech 5.0 2B +15: Granite Speech 5.0 2B 92 (Model card 17, Intended use, limitations, the architecture, the size, the 16K positions and two-minute segments, and the languages are on the card.); Parakeet TDT 0.6B v3 77 (The card misses only a knowledge cut-off (17).)
- Risk, Granite Speech 5.0 2B +10: Granite Speech 5.0 2B 70 (File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in either repository.); Parakeet TDT 0.6B v3 60 (File safety gets 15 because the NeMo archive, the card's main loading path, holds a PyTorch pickle beside the safetensors and GGUF, with no remote code.)
- Agent interface, Granite Speech 5.0 2B +5: Granite Speech 5.0 2B 55 (Chat template 20, chat_template.jinja in the repository (193 characters).); Parakeet TDT 0.6B v3 50 (Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns.)