RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can I run DeepSeek V2 Lite locally?

DeepSeek V2 Lite by deepseek-ai has 16B parameters (2.7B active per token, 64 experts, 6 used per token). At 4-bit with an 8K context it needs about 9.8 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 12 GB of VRAM.

9.8 GBQ4_K_M · 8K context
RTX 3060 12GBsmallest consumer GPU that fits
M2 24GBsmallest Mac that fits
160Kmax context
MLAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K)rough6.2 GB6.3 GB7.0 GB9.9 GB
3-bit (Q3_K_M)usable7.9 GB8.0 GB8.7 GB11.5 GB
4-bit (Q4_K_M)good, most popular9.7 GB9.8 GB10.5 GB13.3 GB
5-bit (Q5_K_M)very good11.1 GB11.3 GB12.0 GB14.8 GB
6-bit (Q6_K)near lossless12.7 GB12.8 GB13.5 GB16.4 GB
8-bit (Q8_0)effectively lossless16.3 GB16.4 GB17.1 GB19.9 GB
16-bit (F16/BF16)original weights30.0 GB30.1 GB30.8 GB33.6 GB

Which GPUs and Macs run DeepSeek V2 Lite?

Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)Details
RTX 3060 12GB12 GBFitsQ4_K_M9.8 GB221details
RTX 4060 Ti 16GB16 GBFitsQ6_K12.8 GB132details
RTX 309024 GBFitsQ8_016.4 GB331details
RTX 409024 GBFitsQ8_016.4 GB357details
RTX 509032 GBFitsQ8_016.4 GB634details
RTX 5070 Ti16 GBFitsQ6_K12.8 GB411details
RX 7900 XTX24 GBFitsQ8_016.4 GB340details
Mac M4 Pro 48GB48 GBFitsQ8_016.4 GB97details
Mac M4 Max 128GB128 GBFitsF1630.1 GB103details
Mac M3 Ultra 512GB512 GBFitsF1630.1 GB154details
DGX Spark128 GBFitsF1630.1 GB51details
RTX 407012 GBFitsQ4_K_M9.8 GB310details
RTX 5060 Ti 16GB16 GBFitsQ6_K12.8 GB205details
RTX 40608 GBFitsQ2_K6.3 GB273details
Arc B58012 GBFitsQ4_K_M9.8 GB280details
RTX 3060 Ti8 GBFitsQ2_K6.3 GB449details
RTX 30708 GBFitsQ2_K6.3 GB449details
RTX 3080 10GB10 GBFitsQ3_K_M8.0 GB584details
RTX 3080 12GB12 GBFitsQ4_K_M9.8 GB561details
RTX 3090 Ti24 GBFitsQ8_016.4 GB357details
RTX 4060 Ti 8GB8 GBFitsQ2_K6.3 GB289details
RTX 4070 Super12 GBFitsQ4_K_M9.8 GB310details
RTX 4070 Ti12 GBFitsQ4_K_M9.8 GB310details
RTX 4070 Ti Super16 GBFitsQ6_K12.8 GB308details
RTX 408016 GBFitsQ6_K12.8 GB329details
RTX 4080 Super16 GBFitsQ6_K12.8 GB337details
RTX 50608 GBFitsQ2_K6.3 GB449details
RTX 507012 GBFitsQ4_K_M9.8 GB413details
RTX 508016 GBFitsQ6_K12.8 GB440details
2x RTX 30902×24 GBFitsF1630.1 GB176details
2x RTX 40902×24 GBFitsF1630.1 GB189details
2x RTX 50902×32 GBFitsF1630.1 GB337details
RTX A600048 GBFitsF1630.1 GB144details
RTX 6000 Ada48 GBFitsF1630.1 GB180details
RTX PRO 6000 Blackwell96 GBFitsF1630.1 GB337details
L40S48 GBFitsF1630.1 GB162details
A100 40GB40 GBFitsF1630.1 GB292details
A100 80GB80 GBFitsF1630.1 GB383details
H100 PCIe80 GBFitsF1630.1 GB376details
H100 SXM80 GBFitsF1630.1 GB629details
H200141 GBFitsF1630.1 GB902details
RX 76008 GBFitsQ2_K6.3 GB289details
RX 7700 XT12 GBFitsQ4_K_M9.8 GB266details
RX 7800 XT16 GBFitsQ6_K12.8 GB286details
RX 7900 GRE16 GBFitsQ6_K12.8 GB264details
RX 7900 XT20 GBFitsQ8_016.4 GB283details
RX 907016 GBFitsQ6_K12.8 GB293details
RX 9070 XT16 GBFitsQ6_K12.8 GB293details
Ryzen AI Max+ 395 128GB128 GBFitsF1630.1 GB48details
Arc A770 16GB16 GBFitsQ6_K12.8 GB257details
Mac M1 16GB16 GBFitsQ3_K_M8.0 GB52details
Mac M2 24GB24 GBFitsQ6_K12.8 GB46details
Mac M3 24GB24 GBFitsQ6_K12.8 GB46details
Mac M4 16GB16 GBFitsQ3_K_M8.0 GB92details
Mac M4 32GB32 GBFitsQ8_016.4 GB42details
Mac M1 Pro 32GB32 GBFitsQ8_016.4 GB71details
Mac M3 Pro 36GB36 GBFitsQ8_016.4 GB53details
Mac M4 Pro 24GB24 GBFitsQ6_K12.8 GB125details
Mac M4 Pro 64GB64 GBFitsF1630.1 GB51details
Mac M1 Max 64GB64 GBFitsF1630.1 GB75details
Mac M2 Max 96GB96 GBFitsF1630.1 GB75details
Mac M3 Max 128GB128 GBFitsF1630.1 GB75details
Mac M4 Max 64GB64 GBFitsF1630.1 GB103details
Mac M2 Ultra 192GB192 GBFitsF1630.1 GB150details
Mac M3 Ultra 256GB256 GBFitsF1630.1 GB154details

Questions

How much VRAM does DeepSeek V2 Lite need?

About 9.8 GB at 4-bit (Q4_K_M) with an 8K context: 8.9 GB of weights (estimated), 0.2 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 16.4 GB.

What is the smallest GPU that runs DeepSeek V2 Lite?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 3060 12GB (12 GB).

Can I run DeepSeek V2 Lite on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M2 24GB or larger, using the default macOS GPU memory limit.

Similar models

Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.

DeepSeek Coder V2 Lite Instruct

16B · 10.5 GB at 4-bit

DeepSeek V2 Lite Chat

16B · 10.5 GB at 4-bit

DeepSeek MoE 16B Base

16B · 12.5 GB at 4-bit

Moonlight 16B A3B Instruct

16B · 10.8 GB at 4-bit

LLaDA2.1 Mini

16B · 10.3 GB at 4-bit

Kimi VL A3B Thinking 2506

16B · 10.8 GB at 4-bit

Embed this

DeepSeek V2 Lite: runs on 12 GB+ VRAM Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.

Copy a snippet

Markdown badge

[![DeepSeek V2 Lite: runs on 12 GB+ VRAM (RunsOnMy)](https://runsonmy.com/badge/deepseek-v2-lite.svg)](https://runsonmy.com/model/deepseek-v2-lite/)

Widget (script)

<div class="runsonmy-widget" data-model="deepseek-v2-lite"><a href="https://runsonmy.com/model/deepseek-v2-lite/">Will DeepSeek V2 Lite run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script>

Widget (iframe)

<iframe src="https://runsonmy.com/embed/m/deepseek-v2-lite/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will DeepSeek V2 Lite run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face repodeepseek-ai/DeepSeek-V2-Lite
Parameters15,706,484,224 (16B) · ~2.7B active (computed from config)
Layers / hidden size27 / 2048
AttentionMLA; 16 heads, 16 KV heads, head dim 128
KV cache per token (FP16)30.4 KiB
Max context163,840 tokens
Licenseother
Released on HFMay 15, 2024
Downloads (30d) / likes117,779 / 210

Sources: Hugging Face model API · config.json (deepseek-ai/DeepSeek-V2-Lite) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.