Qwen3.5 9B (Q5_K_M) — 39.4 GBon Scaleway L4-2-24G

Code Multilingual Thinking Tool Calls Vision

Q5_K_M Scaleway L4-2-24G

Overview

Qwen3.5 9B is a 9.65B parameter dense language model by Qwen, with code, multilingual, thinking, tool-calls, vision capabilities. It supports a context window of up to 262,144 tokens.

Qwen3.5 9B is the flagship small model in Alibaba's Qwen 3.5 family, built on the Gated Delta Networks hybrid architecture with 9.65 billion parameters, outperforming gpt-oss-120B on GPQA Diamond with 81.7 versus 80.1 at thirteen times fewer parameters. It is natively multimodal, processing text, images, and video, with built-in thinking capabilities for chain-of-thought reasoning. The model supports a 262K context window and covers over 201 languages. Released under the Apache 2.0 license, it runs in roughly 5 GB of VRAM at Q4, making it a top choice for self-hosted deployment on consumer hardware.

At Q5_K_M quantization (medium quality tier), the model weighs 6.13 GB. This fits within the 48 GB of VRAM on Scaleway L4-2-24G, enabling full GPU inference.

Hardware Requirements

Model size	6.13 GB
VRAM available	48 GB
VRAM used	39.4 GB
System RAM	96 GB
Min RAM required	0 GB
GPU layers	32 / 32
Context size	262,144
Backend	cuda13
Flash attention	Yes
Reading from disk	Yes

Deploy

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/qwen3-5-9b/q5_k_m/nvidia-l4-48gb.yaml) apply

Generated `values.yaml`

/values/qwen3-5-9b/q5_k_m/nvidia-l4-48gb.yaml

Loading values…

Install llama.cpp

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

Download Model

curl -L -o qwen3-5-9b.gguf "https://huggingface.co/unsloth/Qwen3.5-9B-GGUF/resolve/main/Qwen3.5-9B-Q5_K_M.gguf"

Start Server

llama-server \
  -m qwen3-5-9b.gguf \
  --n-gpu-layers 32 \
  --ctx-size 262144 \
  --flash-attn

Verify

curl http://localhost:8080/health

Frequently Asked Questions

How much VRAM does Qwen3.5 9B (Q5_K_M) need?

The Q5_K_M quantization of Qwen3.5 9B requires 6.13 GB. All 32 layers fit in the 48 GB of VRAM available on Scaleway L4-2-24G, enabling full GPU acceleration.

Can I run Qwen3.5 9B on Scaleway L4-2-24G?

Yes. Scaleway L4-2-24G provides 48 GB of VRAM, which is enough to run Qwen3.5 9B (Q5_K_M) 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. Q5_K_M compresses Qwen3.5 9B from its original size down to 6.13 GB.

What quantization should I choose for Qwen3.5 9B?

Q5_K_M is a medium-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 Qwen3.5 9B on Scaleway L4-2-24G, flash attention is enabled to maximise context length and throughput within the available 48 GB of VRAM.

How do I run Qwen3.5 9B (Q5_K_M) with Ollama?

Run ollama run qwen3.5:9b-q5_k_m to start Qwen3.5 9B (Q5_K_M). Ollama handles downloading the model weights automatically on first run.

Last updated: March 13, 2026