Meta
Llama 4 Maverick 17B 128E (400B parameters) requires approximately 248.4 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 17B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 286 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Llama 4 Maverick 17B 128E on your machine.
Run
lms load Llama-4-Maverick-17B-128E-Instruct && lms server startQuick specs
About this model
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 156.0 GB | Low | — |
Q3_K_S | 3 | 196.0 GB | Low | — |
NVFP4 | 4 | 224.0 GB | Medium | — |
Q4_K_M | 4 | 244.0 GB | Medium | — |
Q5_K_M | 5 | 288.0 GB | High | — |
Q6_K | 6 | 328.0 GB | High | — |
Q8_0 | 8 | 428.0 GB | Very High | — |
F16 | 16 | 820.0 GB | Maximum | — |
Quality benchmarks
Coding
Reasoning
Source: official · 2025-04-05
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Llama 4 Maverick 17B 128E (400B parameters) requires approximately 248.4 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
The recommended quantization for Llama 4 Maverick 17B 128E is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Llama 4 Maverick 17B 128E: AMD Instinct MI350X 288GB (score: 88/100), AMD Instinct MI325X 256GB (score: 75/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Llama 4 Maverick 17B 128E is well-suited for chat as well as reasoning, vision. It was designed with these use cases in mind.
See also