DE

DeepSeek-V2-Lite-Chat

DeepSeekGGUF by second-stateUpdated 2024-07-11
Download on Hugging Face
Parameters15.7B
Context160K
Layers27
Architecturedeepseek2
Smallest quant6.4 GB
Quick answer

DeepSeek-V2-Lite-Chat needs about 13.1 GB of memory at Q4_K_M (a 10.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 13 quants, from 6.4 GB (Q2_K) to 31.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 9.1 GB.

DeepSeek-V2-Lite-Chat: 15.7B parameter MoE model for coding and chat

DeepSeek-V2-Lite-Chat is a 15.7B parameter mixture‑of‑experts model based on the DeepSeek‑2 architecture. It supports a context size of 128000 tokens and is optimized for efficient inference with Multi‑head Latent Attention. The model is available in multiple GGUF quantizations.

Good at

  • Coding assistance
  • Chat interactions
  • Efficient inference on GPUs

Limits

  • Trained context 163840 tokens
  • No vision capability
  • License type: other

Best for

  • Developers building lightweight coding assistants
  • Researchers testing MoE models
  • Deployments on single 40G GPU

Who it’s for. The model is suited for developers and researchers who need a compact yet powerful language model for coding tasks and conversational AI. It can be run on consumer GPUs with appropriate quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.4 GB 9.2 GB
Too big Get file →
Q3_K_S7.5 GB 10.3 GB
Too big Get file →
Q3_K_M8.1 GB 10.9 GB
Too big Get file →
Q3_K_L8.5 GB 11.2 GB
Too big Get file →
Q4_08.9 GB 11.7 GB
Too big Get file →
Q4_K_S9.5 GB 12.3 GB
Too big Get file →
Q4_K_M10.4 GB 13.1 GB
Too big Get file →
Q5_010.8 GB 13.6 GB
Too big Get file →
Q5_K_S11.1 GB 13.9 GB
Too big Get file →
Q5_K_M11.9 GB 14.6 GB
Too big Get file →
Q6_K14.1 GB 16.8 GB
Too big Get file →
Q8_016.7 GB 19.5 GB
Too big Get file →
F1631.4 GB 34.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (6.43 GB file, 9.2 GB memory at 8 k context). For 12 GB VRAM, Q3_K_S (7.49 GB file, 10.3 GB memory). For 16 GB VRAM, Q4_K_M (10.36 GB file, 13.1 GB memory). Estimates are approximate.

What GPU do you need for DeepSeek-V2-Lite-Chat?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q4_0 (8.9 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (11.9 GB file, about 14.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (16.7 GB file, about 19.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (16.7 GB file, about 19.5 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (31.4 GB file, about 34.2 GB in use).

Which DeepSeek-V2-Lite-Chat quant should you choose?

Q4_K_M is the usual starting point for DeepSeek-V2-Lite-Chat: it balances file size and quality well. Here it is a 10.4 GB file.

The Q8_0 file is 16.7 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 6.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters15.7B (approximate, mixture of experts)
Layers27
Trained context163,840 tokens
KV cache (fp16)270 KB per token

Source

Quantized bysecond-state
FamilyDeepSeek
Licenseother
Downloads (HF)1,418
Last updated2024-07-11

Frequently asked questions about DeepSeek-V2-Lite-Chat

How much VRAM does DeepSeek-V2-Lite-Chat need?

About 13.1 GB at Q4_K_M with an 8K context window. That is the 10.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run DeepSeek-V2-Lite-Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek-V2-Lite-Chat GGUF?

It depends on the quant: Q2_K is 6.4 GB, Q3_K_S is 7.5 GB, Q3_K_M is 8.1 GB, Q3_K_L is 8.5 GB, Q4_0 is 8.9 GB, Q4_K_S is 9.5 GB and 7 more.

What context length does DeepSeek-V2-Lite-Chat support?

The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.1 GB at 32K.

Where can I download DeepSeek-V2-Lite-Chat GGUF?

The files are on Hugging Face in the second-state/DeepSeek-V2-Lite-Chat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does DeepSeek-V2-Lite-Chat use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run DeepSeek-V2-Lite-Chat on 8 GB VRAM?

Yes, by using the Q2_K quantization, which requires about 9.2 GB of VRAM at 8 k context.

Is the model fine‑tunable?

The model can be fine‑tuned on 8×80 GB GPUs, as stated in the release notes.

Can I run it on CPU?

It can run on CPU with llama.cpp, but performance will be slower compared to GPU execution.

Other GGUFs of DeepSeek-V2-Lite-Chat

Similar models

Browse all →

More from second-state

All by second-state →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →