Llama 4 Maverick 17B 128E Instruct (Q8_K_XL) — 95.4 GBon Scaleway L4-4-24G

Q8_K_XL Scaleway L4-4-24G

Overview

Llama 4 Maverick 17B 128E Instruct is a 396.58B parameter moe language model by Meta, with code, multilingual, tool-calls, vision capabilities. It supports a context window of up to 1,048,576 tokens.

Llama 4 Maverick 17B 128E Instruct is a large-scale Mixture-of-Experts model from Meta with 17 billion parameters per expert and 128 experts, activating one expert per token for a total of approximately 400 billion parameters. It delivers frontier-class performance on vision, code generation, and multilingual tasks across 12 languages. Maverick represents the high-capacity tier of the Llama 4 family, trading higher memory requirements for stronger benchmark results. With a 1M token context window, it requires multi-GPU setups but quantizes down to Q2 levels.

At Q8_K_XL quantization (high quality tier), the model weighs 428.4 GB. This exceeds the 96 GB of VRAM on Scaleway L4-4-24G. Inference is still possible via CPU offload or memory-mapped loading from disk, but expect significantly reduced performance.

Hardware Requirements

Model size	428.4 GB
VRAM available	96 GB
VRAM used	95.4 GB
System RAM	192 GB
Min RAM required	427.6 GB
GPU layers	48 / 48
Context size	509,652
Backend	cuda13
Flash attention	Yes
Reading from disk	Yes

Performance Notes

Mixture-of-Experts

This is a Mixture-of-Experts model with 128 total experts, of which 1 are active per token. Only the active experts need fast GPU access — inactive expert weights can reside in system RAM with minimal impact on generation speed.

Read the MoE deployment guide →

Minimal performance impact

All expert weights offloaded to CPU — only 1/128 experts are activated per token, so the performance impact is negligible.

Major performance impact

The model size exceeds available VRAM + RAM. Data will be read from disk on demand, which significantly slows inference.

Shorter conversations

Context size has been reduced due to memory constraints. This may affect the model's ability to handle long conversations.

Deploy

Server Local

Prerequisites

Ensure your GPU nodes are prepared with the NVIDIA container toolkit:

ansible-playbook prositronic.infra.nvidia_container_toolkit

Command

helmfile --state-values-file <(curl -s https://www.prositronic.eu/values/llama-4-maverick-17b-128e-instruct/q8_k_xl/nvidia-l4-96gb.yaml) apply

Generated values.yaml

/values/llama-4-maverick-17b-128e-instruct/q8_k_xl/nvidia-l4-96gb.yaml

Loading values…

Install llama.cpp

Install llama.cpp from the official build instructions for your platform and backend.

Download Model

curl -L -o llama-4-maverick-17b-128e-instruct.gguf "https://huggingface.co/unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF/resolve/main/UD-Q8_K_XL/Llama-4-Maverick-17B-128E-Instruct-UD-Q8_K_XL-00001-of-00010.gguf"

Start Server

llama-server \
  -m llama-4-maverick-17b-128e-instruct.gguf \
  --n-gpu-layers 48 \
  --ctx-size 509652 \
  --flash-attn \
  -ot ".ffn_.*_exps.=CPU"

Verify

curl http://localhost:8080/health

Explore

• Configure a deployment
• Browse models
• Browse hardware

Other quantizations

• Llama 4 Maverick 17B 128E Instruct (Q8_0)
• Llama 4 Maverick 17B 128E Instruct (Q5_K_M)
• Llama 4 Maverick 17B 128E Instruct (Q4_K_M)

Other hardware

• Llama 4 Maverick 17B 128E Instruct on CPU Only
• Llama 4 Maverick 17B 128E Instruct on NVIDIA A100 80GB
• Llama 4 Maverick 17B 128E Instruct on NVIDIA H100

Frequently Asked Questions

How much VRAM does Llama 4 Maverick 17B 128E Instruct (Q8_K_XL) need?

The Q8_K_XL quantization of Llama 4 Maverick 17B 128E Instruct requires 428.4 GB. All 48 layers fit in the 96 GB of VRAM available on Scaleway L4-4-24G, enabling full GPU acceleration.

Can I run Llama 4 Maverick 17B 128E Instruct on Scaleway L4-4-24G?

Yes. Scaleway L4-4-24G provides 96 GB of VRAM, which is enough to run Llama 4 Maverick 17B 128E Instruct (Q8_K_XL) with all layers on the GPU for optimal performance.

What is quantization?

Quantization reduces a model's numerical precision from its original floating-point format to a more compact representation. This shrinks the file size and VRAM footprint, making it possible to run large models on consumer hardware. The trade-off is a small reduction in output quality. Q8_K_XL compresses Llama 4 Maverick 17B 128E Instruct from its original size down to 428.4 GB.

What quantization should I choose for Llama 4 Maverick 17B 128E Instruct?

Q8_K_XL is a high-quality quantization. Higher-quality quants (Q8, Q6) preserve more model accuracy but need more VRAM. Lower quants (Q4, Q3, Q2) reduce VRAM usage at the cost of some quality. Choose based on your available hardware and quality requirements.

What is flash attention and why is it enabled?

Flash attention is a memory-efficient algorithm that speeds up the attention mechanism in transformer models. It reduces VRAM usage during inference by avoiding the materialisation of the full attention matrix. For Llama 4 Maverick 17B 128E Instruct on Scaleway L4-4-24G, flash attention is enabled to maximise context length and throughput within the available 96 GB of VRAM.

What is MoE and how does it affect deployment?

Llama 4 Maverick 17B 128E Instruct uses a Mixture-of-Experts (MoE) architecture with 128 experts, of which 1 are active per token. This means only a fraction of the model weights are used for each inference step, allowing MoE models to be larger in total parameter count while remaining efficient at inference time.

How do I run Llama 4 Maverick 17B 128E Instruct (Q8_K_XL) with Ollama?

Run ollama run llama4:17b-maverick-128e-instruct-q8_k_xl to start Llama 4 Maverick 17B 128E Instruct (Q8_K_XL). Ollama handles downloading the model weights automatically on first run.

Last updated: March 5, 2026