Llama 4 Maverick 400BvsLlama 4 Scout 109B
Complete comparison between Llama 4 Maverick 400B (400B parameters, Meta) and Llama 4 Scout 109B (109B, Meta). VRAM required by quantization, tokens per second measured on 4 reference GPUs, verdict by use case, license, and installation commands. All figures are calculated from catalog data—no copy-pasting between pages.
In brief
| Feature | Llama 4 Maverick 400B | Llama 4 Scout 109B |
|---|---|---|
| Settings | 400B | 109B |
| Family | Llama | Llama |
| Author | Meta | Meta |
| Origin | US | US |
| License | Llama 4 Community | Llama 4 Community |
| Context | 1,000,000 tokens | 10,000,000 tokens |
| Output | April 2025 | April 2025 |
Memory footprint
Approximate VRAM required for inference with an average context window. The winner (in green) is the model that uses less — smaller models have the edge.
| Quantization | Llama 4 Maverick 400B | Llama 4 Scout 109B |
|---|---|---|
| Q4_K_M (lightweight) | 240 GB | 65 GB |
| Q5_K_M (balanced) | 285 GB | 78 GB |
| Q8 (near-lossless) | 425 GB | 117 GB |
| FP16 (max quality) | 800 GB | 218 GB |
| CPU-only RAM | 280 GB | 100 GB |
Estimated speed (tokens/second)
Estimates based on the best quantization that can fit on each GPU. Actual figures depend on the prompt, context, and engine (llama.cpp, vLLM, MLX). Methodology.
| Reference GPU | Llama 4 Maverick 400B | Llama 4 Scout 109B |
|---|---|---|
| RTX 4090 (24 GB) | ✗ too heavy | ✗ too heavy |
| RTX 4080 (16 GB) | ✗ too heavy | ✗ too heavy |
| RTX 3060 12GB (12 GB) | ✗ too heavy | ✗ too heavy |
| Apple M4 Pro (48 GB) (36 GB) | ✗ too heavy | ✗ too heavy |
Verdict by use case
For each common use case, we indicate which of the two is better suited based on its tags, size, and specialization.
Your private, free ChatGPT on your machine in 1 hour — LM Studio, Ollama, Open WebUI, your documents, no cloud.
- Lifetime online access
- PDF + files
- 30-day money-back guarantee
Strengths and weaknesses
Llama 4 Maverick 400B
400B/17B active MoE (128 experts), natively multimodal. LMArena 1417. 245 GB to download.
- LMArena 1417
- MMLU-Pro 80
- 1M context
- Multimodal
- 245 GB download
- HF gated
- Clause >700M MAU
Installation
Llama 4 Scout 109B
109B/17B active MoE, native multimodal, 10M context. Fits on an H100. HF gated.
- 10M context (!)
- Fits on an H100
- Native vision
- HF gated
- Llama 4 license (clause >700M MAU)
Installation
Frequently asked questions
Which model runs best on RTX 4090 (24 GB): Llama 4 Maverick 400B or Llama 4 Scout 109B?
On an RTX 4090, Llama 4 Maverick 400B doesn't fit in 24 GB — part of it must be offloaded to the CPU, and Llama 4 Scout 109B doesn't fit in 24 GB either. See the configurator to test your exact GPU.
Which uses the least VRAM?
In Q4_K_M, Llama 4 Scout 109B fits in 65 GB versus 240 GB for its rival—a 175 GB gap, significant if you're targeting an RTX 3060 or a 4060 Ti 8 GB.
Can these models be used in commercial production?
Llama 4 Maverick 400B is under Llama 4 Community — check the restrictions (especially the monthly user thresholds). Llama 4 Scout 109B is under Llama 4 Community — also check the terms. For SaaS, prefer Apache 2.0 or MIT.
Which one should you choose in 2026?
Depends on your primary constraint. Smaller / faster: Llama 4 Scout 109B (109B). More capable: Llama 4 Maverick 400B (400B). If you're unsure, run it configurator with your GPU and use case — it will decide based on both.
Alternatives to consider
If neither works for you, here are some neighboring models you could explore.