Llama-4-Maverick-17B-128E-Instruct
Params
401.6 B
Context
—
Downloads 30d
9 K
Likes
517
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)9 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 803.2 GB | 944.2 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.19
input / 1M
$0.65
output / 1M
$0.05
cached input / 1M
$0.84
1M in + 1M out
- Context window
- 128,000 tokens
- Max output
- 16,384 tokens
- Providers
- 3
- Cheapest provider
- DigitalOcean · $0.19 / $0.65
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 9.3 / 16.3 / 0.6
✓ Tool calling
✗ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Llama4ForConditionalGeneration
- Parameters
- 401.6 B
- Tensor type
- BF16
- Licence
- other
- First seen on the Hub
- 2025-04-01
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any image-text-to-text model