Meta Llama 3.1 8B Instruct
unsloth · released 2024-07-23 · llama3.1 license
Llama 3.1 8B Instruct is Meta's general-purpose 8B (Dec-2023 cutoff): vendor MMLU-Pro 48.3, IFEval 80.4, strong instruction-following and tool use, weaker on graduate science (GPQA 30.4).
Key specs
| Type | Local open-weight |
|---|---|
| Parameters | 8.03B total |
| Architecture | llama |
| Context window | 131K tokens |
| Knowledge cutoff | 2023-12-01 |
| Modalities | text |
| Recommended backends | — |
| Minimum viable rig | — |
Benchmark scores
| GPQA Diamond | — |
|---|---|
| SWE-bench Verified | — |
| AIME | — |
| MMLU-Pro | 48.3% |
| BFCL v3 (tool use) | — |
| Composite score | 6.15 |
| Community rating | No reviews yet |
VRAM & disk per quantization
| Quant | VRAM | Disk | RAM | Context |
|---|---|---|---|---|
| Q4_K_M | 6.2 GB | 4.7 GB | — | 131K |
Strengths & weaknesses
Strengths: Strong all-round small model (MMLU-Pro 48.3, IFEval 80.4); Good tool use (BFCL 76.1) and 128K context; Widely supported
Weaknesses: Low GPQA (vendor 30.4); Pre-reasoning-era; no AIME results