Llama 4 Scout by Meta — 109B MoE (17B active) open-weight local LLM. License: Llama 4 Community. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.
Key specs
| Type | Local open-weight |
|---|
| Parameters | 109B total · MoE, 17B active |
|---|
| Architecture | MoE (16 experts) |
|---|
| Context window | — |
|---|
| Knowledge cutoff | 2024-08-01 |
|---|
| Modalities | text, image |
|---|
| Recommended backends | — |
|---|
| Minimum viable rig | — |
|---|
Benchmark scores
| GPQA Diamond | 57% |
|---|
| SWE-bench Verified | 32% |
|---|
| AIME | 45% |
|---|
| MMLU-Pro | 74% |
|---|
| BFCL v3 (tool use) | 60% |
|---|
| Composite score | 5.22 |
|---|
| Community rating | No reviews yet |
|---|
VRAM & disk per quantization
| Quant | VRAM | Disk | RAM | Context |
|---|
| Q4_K_M | 62 GB | 55 GB | 80 GB | 10000K |
| Q8 | 118 GB | 109 GB | 128 GB | 10000K |
| FP16 | 230 GB | 218 GB | 256 GB | 10000K |
API pricing (per 1M tokens)
| Provider | Input | Output | Free tier |
|---|
| Groq | $0.11 | $0.34 | No |
| Together AI | $0.18 | $0.59 | No |