DeepSeek14B~9 GB VRAM at Q4_K_M

DeepSeek R1 Distill Qwen 14B — VRAM, speed & local setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated January 20, 2025

The ideal R1 distill for RTX 3060/4070 users. Exceptional reasoning in 10GB VRAM — better logical performance than most non-reasoning 70B models.

DeepSeek R1 Distill Qwen 14B needs about 9 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic94

Creative76

Coding90

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

Quant	VRAM	Speed (est.)	Fit
Q2_K 2.63 bpw	6.7 GB	~108 tok/s	Fits
Q3_K_M 3.41 bpw	8.1 GB	~91 tok/s	Fits
Q4_K_M 4.83 bpw	10.6 GB	~70 tok/s	Fits
Q5_K_M 5.67 bpw	12.1 GB	~62 tok/s	Fits
Q6_K 6.56 bpw	13.6 GB	~55 tok/s	Fits
Q8_0 8.50 bpw	17 GB	~44 tok/s	Fits
F16 16.00 bpw	30.1 GB	~4 tok/s	Offload

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. DeepSeek R1 Distill Qwen 14B VRAM calculator →

Get DeepSeek R1 Distill Qwen 14B running

The cheapest catalogued GPU that runs DeepSeek R1 Distill Qwen 14B is the Intel Arc B580 (12 GB).

Buy this hardware Intel Arc B580 12GB — 12 GB VRAM · 190 W board power Deploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Intel Arc B580 12GB

12 GB VRAM · 190 W board power

2026 prices are volatile — check the current listing.

Check price on Amazon

How to run DeepSeek R1 Distill Qwen 14B

Install Ollama, then run:

$ollama run deepseek-r1:14b

Weights on Hugging Face: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B ↗

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters: 14 Billion
Context window: 128,000
Architecture: Dense
Provider: DeepSeek
Licence: MIT
Practical deployment: Laptop
Specified at: Q4_K_M
System RAM: 16 GB
Record updated: 2025-01-20

LicenceMITCommercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forreasoningmathcoding

Can I run DeepSeek R1 Distill Qwen 14B on my GPU?

Other DeepSeek R1 sizes

DeepSeek R1 Distill Qwen 14B — frequently asked questions

How much VRAM does DeepSeek R1 Distill Qwen 14B need?

About 9 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does DeepSeek R1 Distill Qwen 14B run on an RTX 4090 (24 GB)?

Yes. DeepSeek R1 Distill Qwen 14B needs about 9 GB at Q4_K_M, inside a 24 GB card, at an estimated 70 tokens/sec.

How do I run DeepSeek R1 Distill Qwen 14B locally?

Install Ollama and run `ollama run deepseek-r1:14b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does DeepSeek R1 come in?

DeepSeek R1 Distill Llama 8B (6 GB), DeepSeek R1 Distill Qwen 32B (20 GB), DeepSeek R1 Distill Qwen 14B (9 GB), DeepSeek R1 (671B) (406 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.