Meta
Llama 4 Maverick 17B 128E
前沿
35.9K下载量489点赞Apr 2025发布日期1.0M tokens上下文Llama 4 Community许可证81 优秀质量
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.
快速开始
— 复制粘贴即可本地运行Copy-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
Parameters400B (17B active)
Architecturemoe (MoE)
Context1.0M tokens
Modalitytext+vision
Min RAM156 GB
Rec. RAM244 GB (Q4_K_M)
LicenseLlama 4 Community
FamilyLlama
✓ Vision✓ Chat✓ Reasoning
About this model
相关模型
快速推荐
最佳硬件
Llama 4 Maverick 17B 128E 的最佳选择
运行此模型
量化选项
各量化级别的 VRAM 估算
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
Llama 4 Maverick 17B 128E benchmark scores
Coding
SWE-bench Verified—
HumanEval+—
Aider Polyglot—
LiveCodeBench43.4%
Reasoning
MMLU-Pro80.5%
GPQA Diamond69.8%
MATH-50061.2%
ARC Challenge—
Source: official · 2025-04-05
硬件兼容性
全部硬件的适配估算
Computing compatibility...
内存详细分析
Reference: RTX 2060 6GB
Weights244.0 GB
KV Cache2.9 GB
Runtime0.9 GB
Headroom0.6 GB
常见问题
FAQ — Llama 4 Maverick 17B 128E
另请参阅