# Model datasheets

> Open-weight models with architecture verified against config.json and GGUF sizes from the HF API.

Canonical: https://thelocalbench.com/models · Data as of 2026-10-12 · The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0

Flags: [verified] checked against primary source · [sourced] cited · [estimate] formula · [sample] placeholder

| Model | Org | Params (B) | Active (B) | Context | Default quant | File GB | Licence |
|---|---|---|---|---|---|---|---|
| [Llama 3.1 8B Instruct](/models/llama-3.1-8b.md) | Meta | 8.03 | 8.03 | 131072 | Q4_K_M | 4.92 [verified] | Llama 3.1 Community License |
| [Qwen3 8B](/models/qwen3-8b.md) | Alibaba Qwen | 8.19 | 8.19 | 32768 | Q4_K_M | 5.03 [verified] | Apache-2.0 |
| [Qwen3 14B](/models/qwen3-14b.md) | Alibaba Qwen | 14.77 | 14.77 | 32768 | Q4_K_M | 9 [verified] | Apache-2.0 |
| [gpt-oss-20b](/models/gpt-oss-20b.md) | OpenAI | 20.91 | 3.6 | 131072 | MXFP4 | 12.11 [verified] | Apache-2.0 |
| [Mistral Small 3.2 24B](/models/mistral-small-3.2-24b.md) | Mistral AI | 24.01 | 24.01 | 131072 | Q4_K_M | 14.33 [verified] | Apache-2.0 |
| [Gemma 3 27B IT](/models/gemma-3-27b.md) | Google DeepMind | 27.43 | 27.43 | 131072 | Q4_K_M | 16.55 [verified] | Gemma Terms of Use |
| [Qwen3 30B-A3B](/models/qwen3-30b-a3b.md) | Alibaba Qwen | 30.53 | 3.3 | 32768 | Q4_K_M | 18.56 [verified] | Apache-2.0 |
| [Qwen3 32B](/models/qwen3-32b.md) | Alibaba Qwen | 32.76 | 32.76 | 32768 | Q4_K_M | 19.76 [verified] | Apache-2.0 |
| [Llama 3.3 70B Instruct](/models/llama-3.3-70b.md) | Meta | 70.55 | 70.55 | 131072 | Q4_K_M | 42.52 [verified] | Llama 3.3 Community License |
| [gpt-oss-120b](/models/gpt-oss-120b.md) | OpenAI | 116.83 | 5.1 | 131072 | MXFP4 | 63.39 [verified] | Apache-2.0 |