Compare models
Mistral 7B Instruct v0.3 vs Llama 3.3 70B Instruct vs Qwen2.5 Coder 32B Instruct
Every figure below carries the source that reported it and the moment it was observed. Values that failed validation are withheld rather than shown, and a dash means no source we track carries that field for that model.
| Field | Mistral 7B Instruct v0.3 | Llama 3.3 70B Instruct | Qwen2.5 Coder 32B Instruct |
|---|---|---|---|
| Downloads, 30 days | 2,332,647 (highest of the compared values)Synced from sourceCurrent1h ago | 917,910Synced from sourceCurrent1h ago | 1,215,982Synced from sourceCurrent1h ago |
| Likes | 3,531 (highest of the compared values)Synced from sourceCurrent1h ago | 3,058Synced from sourceCurrent1h ago | 2,152Synced from sourceCurrent1h ago |
| Context window | — | 131,072 (highest of the compared values)Synced from sourceCurrent1h ago | 32,768Synced from sourceCurrent1h ago |
| Input, $/M tokens | — | 0.1 (lowest of the compared values)Synced from sourceCurrent1h ago | 0.66Synced from sourceCurrent1h ago |
| Modality | textSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago | codeSeeded, unreviewedwritten 29d ago |
| Licence | apache-2.0Seeded, unreviewedwritten 29d ago | llama-3.3Seeded, unreviewedwritten 29d ago | apache-2.0Seeded, unreviewedwritten 29d ago |
| Gated | noSynced from sourceCurrent1h ago | manualSynced from sourceCurrent1h ago | noSynced from sourceCurrent1h ago |
| Last updated | 2025-12-03Synced from sourceCurrent1h ago | 2024-12-21Synced from sourceCurrent1h ago | 2025-01-12Synced from sourceCurrent1h ago |
| Library | vllmSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago |
| Task | — | text-generationSynced from sourceCurrent1h ago | text-generationSynced from sourceCurrent1h ago |
| Hugging Face | mistralai/Mistral-7B-Instruct-v0.3Synced from sourceCurrent1h ago | meta-llama/Llama-3.3-70B-InstructSynced from sourceCurrent1h ago | Qwen/Qwen2.5-Coder-32B-InstructSynced from sourceCurrent1h ago |
| OpenRouter id | — | meta-llama/llama-3.3-70b-instructSynced from sourceCurrent1h ago | qwen/qwen-2.5-coder-32b-instructSynced from sourceCurrent1h ago |
| Output, $/M tokens | — | 0.32Synced from sourceCurrent1h ago | 1Synced from sourceCurrent1h ago |
| Vendor | Mistral AISeeded, unreviewedwritten 29d ago | MetaSeeded, unreviewedwritten 29d ago | AlibabaSeeded, unreviewedwritten 29d ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 1h ago. Where a row is marked, ▲ is the highest of the values shown and ▼ the lowest — arithmetic on the figures above, not a ranking or a recommendation. Rows where neither extreme is meaningful are left unmarked rather than given a direction they do not have.
Change the comparison
Remove one, or open the directory to pick a different set. Up to 3 at a time.