DeepSeek R1 Distill Qwen 32B (Q5_K_M) — 31.4 GBon NVIDIA V100S

Q5_K_M NVIDIA V100S

Overview

DeepSeek R1 Distill Qwen 32B is a 32.76B parameter dense language model by DeepSeek, with code, multilingual, thinking, tool-calls capabilities. It supports a context window of up to 131,072 tokens.

DeepSeek R1 Distill Qwen 32B is a 32.76-billion-parameter dense transformer from DeepSeek, distilled from the larger R1 reasoning model into a Qwen-based architecture. It excels at chain-of-thought reasoning, code generation, and multilingual tasks with built-in thinking capabilities. Compared to standard 30B-class instruct models, it provides stronger logical and mathematical reasoning. The model supports nine languages and a 128K context window, making it suitable for developers and researchers who need reasoning-focused inference on mid-range GPU setups.

At Q5_K_M quantization (medium quality tier), the model weighs 21.66 GB. This fits within the 32 GB of VRAM on NVIDIA V100S, enabling full GPU inference.

Hardware Requirements

Model size	21.66 GB
VRAM available	32 GB
VRAM used	31.4 GB
GPU layers	64 / 64
Context size	55,674
Backend	cuda13
Flash attention	Yes

Performance Notes

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/deepseek-r1-distill-qwen-32b/q5_k_m/nvidia-v100s.yaml) apply

Generated values.yaml

/values/deepseek-r1-distill-qwen-32b/q5_k_m/nvidia-v100s.yaml

Loading values…

Install llama.cpp

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

Download Model

curl -L -o deepseek-r1-distill-qwen-32b.gguf "https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-32B-Q5_K_M.gguf"

Start Server

llama-server \
  -m deepseek-r1-distill-qwen-32b.gguf \
  --n-gpu-layers 64 \
  --ctx-size 55674 \
  --flash-attn

Verify

curl http://localhost:8080/health

Explore

• Configure a deployment
• Browse models
• Browse hardware

Other quantizations

• DeepSeek R1 Distill Qwen 32B (FP16)
• DeepSeek R1 Distill Qwen 32B (Q8_0)
• DeepSeek R1 Distill Qwen 32B (Q4_K_M)

Other hardware

• DeepSeek R1 Distill Qwen 32B on CPU Only
• DeepSeek R1 Distill Qwen 32B on NVIDIA A100 80GB
• DeepSeek R1 Distill Qwen 32B on NVIDIA H100

Frequently Asked Questions

How much VRAM does DeepSeek R1 Distill Qwen 32B (Q5_K_M) need?

The Q5_K_M quantization of DeepSeek R1 Distill Qwen 32B requires 21.66 GB. All 64 layers fit in the 32 GB of VRAM available on NVIDIA V100S, enabling full GPU acceleration.

Can I run DeepSeek R1 Distill Qwen 32B on NVIDIA V100S?

Yes. NVIDIA V100S provides 32 GB of VRAM, which is enough to run DeepSeek R1 Distill Qwen 32B (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 DeepSeek R1 Distill Qwen 32B from its original size down to 21.66 GB.

What quantization should I choose for DeepSeek R1 Distill Qwen 32B?

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 DeepSeek R1 Distill Qwen 32B on NVIDIA V100S, flash attention is enabled to maximise context length and throughput within the available 32 GB of VRAM.

How do I run DeepSeek R1 Distill Qwen 32B (Q5_K_M) with Ollama?

Run ollama run deepseek-r1:32b-qwen-distill-q5_k_m to start DeepSeek R1 Distill Qwen 32B (Q5_K_M). Ollama handles downloading the model weights automatically on first run.

Last updated: March 5, 2026