Check my GPU

LLMs ·

DeepSeek MoE 16B Chat

Parameters
16B (2.8B active)
Architecture
Mixture of experts
Max context
4K tokens
License
deepseek
Released
2024-01

How to run it

Quantized files · GGUF

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

huggingface.co/mradermacher/deepseek-moe-16b-chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/deepseek-moe-16b-chat-i1-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/deepseek-moe-16b-chat (opens in a new tab)

No sign-in needed.

Links checked 6 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.

Quantization Quality Weights Total at 4K context Download
Q2_K Low 6.6 GB 8.1 GB GGUF (opens in a new tab)
Q3_K_M Low 8.0 GB 9.6 GB GGUF (opens in a new tab)
Q4_K_M Good 10.0 GB 11.5 GB GGUF (opens in a new tab)
Q5_K_M High 11.6 GB 13.2 GB GGUF (opens in a new tab)
Q6_K High 13.4 GB 15.0 GB GGUF (opens in a new tab)
Q8_0 Very high 17.4 GB 18.9 GB GGUF files (opens in a new tab)
F16 Full 32.8 GB 34.3 GB Original weights (opens in a new tab)

Best hardware for DeepSeek MoE 16B Chat

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B570 (launch price $219) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q8_0 20.1 GB / 24.0 GB 92.2 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q8_0 20.1 GB / 24.0 GB 104 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q8_0 20.1 GB / 24.0 GB 112 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15 NVIDIA GeForce RTX 5090 Q8_0 20.5 GB / 32.0 GB 200 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q4_K_M 12.3 GB / 16.0 GB 121 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M4 Pro (24 GB) Q4_K_M 12.8 GB / 16.1 GB 51.5 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Ti 16GB Q4_K_M 12.3 GB / 16.0 GB 63.1 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q4_K_M 12.3 GB / 16.0 GB 147 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q4_K_M 12.3 GB / 16.0 GB 161 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5060 Ti 16GB Q4_K_M 12.3 GB / 16.0 GB 98.2 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.