Check my GPU

LLMs ·

DeepSeek V2 Lite Chat

Parameters
16B (2.4B active)
Architecture
Mixture of experts
Max context
160K tokens
License
deepseek
Released
2024-05

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run deepseek-v2:16b

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/mradermacher/DeepSeek-V2-Lite-Chat-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/DeepSeek-V2-Lite-Chat-GGUF

Original weights · Hugging Face

Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.

huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: latent (MLA) KV cache.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 6.3 GB 7.1 GB 7.9 GB GGUF (opens in a new tab)
Q3_K_M Low 7.7 GB 8.6 GB 9.3 GB GGUF (opens in a new tab)
Q4_K_M Good 9.6 GB 10.4 GB 11.2 GB GGUF (opens in a new tab)
Q5_K_M High 11.2 GB 12.0 GB 12.8 GB GGUF (opens in a new tab)
Q6_K High 12.9 GB 13.7 GB 14.5 GB GGUF (opens in a new tab)
Q8_0 Very high 16.7 GB 17.5 GB 18.3 GB GGUF (opens in a new tab)
F16 Full 31.4 GB 32.3 GB 33.0 GB Original weights (opens in a new tab)

Best hardware for DeepSeek V2 Lite Chat

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A580 (launch price $179) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q8_0 18.7 GB / 24.0 GB 108 tok/s Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q8_0 18.7 GB / 24.0 GB 122 tok/s Runs well
73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q8_0 18.7 GB / 24.0 GB 131 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q5_K_M 12.8 GB / 16.0 GB 116 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M4 Pro (24 GB) Q5_K_M 13.3 GB / 16.1 GB 49.7 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Ti 16GB Q5_K_M 12.8 GB / 16.0 GB 60.8 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q5_K_M 12.8 GB / 16.0 GB 142 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q5_K_M 12.8 GB / 16.0 GB 155 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5060 Ti 16GB Q5_K_M 12.8 GB / 16.0 GB 94.6 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q5_K_M 12.8 GB / 16.0 GB 189 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.