DeepSeek R1 Distill Qwen 7B (Q2_K_L) — 11.2 GBon NVIDIA RTX 5070 Ti

Code Multilingual Thinking Tool Calls

Q2_K_L NVIDIA RTX 5070 Ti

Overview

DeepSeek R1 Distill Qwen 7B is a 7.62B 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 7B is a 7.62-billion-parameter dense transformer from DeepSeek, distilled from the R1 reasoning model into a compact Qwen-based architecture. It brings chain-of-thought reasoning and thinking capabilities to the 7B parameter class, performing above its weight on math and logic tasks. Compared to standard 7B instruct models, it offers noticeably stronger structured reasoning. With a 128K context window and nine supported languages, it fits on a single consumer GPU and quantizes well for efficient self-hosted deployment.

At Q2_K_L quantization (low quality tier), the model weighs 2.93 GB. This fits within the 16 GB of VRAM on NVIDIA RTX 5070 Ti, enabling full GPU inference.

Hardware Requirements

Model size	2.93 GB
VRAM available	16 GB
VRAM used	11.2 GB
System RAM
Min RAM required	0 GB
GPU layers	28 / 28
Context size	131,072
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/deepseek-r1-distill-qwen-7b/q2_k_l/nvidia-rtx5070ti.yaml) apply

Generated `values.yaml`

/values/deepseek-r1-distill-qwen-7b/q2_k_l/nvidia-rtx5070ti.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-7b.gguf "https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-Q2_K_L.gguf"

Start Server

llama-server \
  -m deepseek-r1-distill-qwen-7b.gguf \
  --n-gpu-layers 28 \
  --ctx-size 131072 \
  --flash-attn

Verify

curl http://localhost:8080/health

Frequently Asked Questions

How much VRAM does DeepSeek R1 Distill Qwen 7B (Q2_K_L) need?

The Q2_K_L quantization of DeepSeek R1 Distill Qwen 7B requires 2.93 GB. All 28 layers fit in the 16 GB of VRAM available on NVIDIA RTX 5070 Ti, enabling full GPU acceleration.

Can I run DeepSeek R1 Distill Qwen 7B on NVIDIA RTX 5070 Ti?

Yes. NVIDIA RTX 5070 Ti provides 16 GB of VRAM, which is enough to run DeepSeek R1 Distill Qwen 7B (Q2_K_L) 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. Q2_K_L compresses DeepSeek R1 Distill Qwen 7B from its original size down to 2.93 GB.

What quantization should I choose for DeepSeek R1 Distill Qwen 7B?

Q2_K_L is a low-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 7B on NVIDIA RTX 5070 Ti, flash attention is enabled to maximise context length and throughput within the available 16 GB of VRAM.

How do I run DeepSeek R1 Distill Qwen 7B (Q2_K_L) with Ollama?

Run ollama run deepseek-r1:7b-qwen-distill-q2_k_l to start DeepSeek R1 Distill Qwen 7B (Q2_K_L). Ollama handles downloading the model weights automatically on first run.

Last updated: March 7, 2026