DE

DeepSeek Coder V2 Instruct

DeepSeekGGUF by gaianetUpdated 2024-08-06
Download on Hugging Face
Parameters236B
Context160K
Layers60
Architecturedeepseek2
Smallest quant85.9 GB
Quick answer

DeepSeek Coder V2 Instruct needs about 183.2 GB of memory at Q4_K_M (a 142.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 85.9 GB (Q2_K) to 471.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 161.1 GB.

DeepSeek Coder V2 Instruct – 236B MoE code model

DeepSeek Coder V2 Instruct is a 236B parameter Mixture‑of‑Experts model focused on coding tasks. It supports 128K context and 338 programming languages. The model is available in multiple GGUF quantizations for local inference.

Good at

  • Code completion
  • Mathematical reasoning
  • Multi‑language support

Limits

  • Requires large VRAM for high‑precision quant
  • No vision capabilities
  • License is other

Best for

  • Local code generation
  • Debugging assistance
  • Educational coding tools

Who it’s for. Developers and researchers needing a large code‑centric model that can run locally with quantization. It is suitable for teams that prefer open‑source MoE models and can manage the memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K85.9 GB (3 parts) 126.7 GB
Too big Get file →
Q3_K_S101.7 GB (4 parts) 142.4 GB
Too big Get file →
Q3_K_M112.7 GB (4 parts) 153.4 GB
Too big Get file →
Q3_K_L122.4 GB (5 parts) 163.1 GB
Too big Get file →
Q4_0132.9 GB (5 parts) 173.7 GB
Too big Get file →
Q4_K_S133.9 GB (5 parts) 174.6 GB
Too big Get file →
Q4_K_M142.5 GB (5 parts) 183.2 GB
Too big Get file →
Q5_0162.3 GB (6 parts) 203.1 GB
Too big Get file →
Q5_K_S162.3 GB (6 parts) 203.1 GB
Too big Get file →
Q5_K_M167.2 GB (6 parts) 208.0 GB
Too big Get file →
Q6_K193.5 GB (7 parts) 234.3 GB
Too big Get file →
Q8_0250.6 GB (9 parts) 291.4 GB
Too big Get file →
F16471.6 GB (17 parts) 512.4 GB
Too big Get file →

For 8 GB VRAM, use Q2_K or Q3_K_S. For 16 GB VRAM, Q4_K_S or Q4_K_M are suitable. For 32 GB VRAM, Q5_K_M or Q6_K provide a good balance between quality and memory usage. Estimates are approximate.

What GPU do you need for DeepSeek Coder V2 Instruct?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which DeepSeek Coder V2 Instruct quant should you choose?

Q4_K_M is the usual starting point for DeepSeek Coder V2 Instruct: it balances file size and quality well. Here it is a 142.5 GB file.

The Q8_0 file is 250.6 GB, about 1.8 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 85.9 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
Parameters236B (approximate, mixture of experts)
Layers60
Trained context163,840 tokens
KV cache (fp16)4800 KB per token

Source

Quantized bygaianet
FamilyDeepSeek
Licenseother
Downloads (HF)632
Last updated2024-08-06

Frequently asked questions about DeepSeek Coder V2 Instruct

How much VRAM does DeepSeek Coder V2 Instruct need?

About 183.2 GB at Q4_K_M with an 8K context window. That is the 142.5 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 Coder V2 Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 126.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek Coder V2 Instruct GGUF?

It depends on the quant: Q2_K is 85.9 GB, Q3_K_S is 101.7 GB, Q3_K_M is 112.7 GB, Q3_K_L is 122.4 GB, Q4_0 is 132.9 GB, Q4_K_S is 133.9 GB and 7 more.

What context length does DeepSeek Coder V2 Instruct support?

The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 40.3 GB at 8K and 161.1 GB at 32K.

Where can I download DeepSeek Coder V2 Instruct GGUF?

The files are on Hugging Face in the gaianet/DeepSeek-Coder-V2-Instruct-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 Coder V2 Instruct 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 Coder V2 on 8 GB VRAM?

Use the Q2_K or Q3_K_S quantization; they require about 126.7 GB or 142.4 GB of VRAM at 8K context, which is not feasible on 8 GB. Lower‑rank quantizations are needed.

Does the model support image input?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a context length of 128000 tokens.

Other GGUFs of DeepSeek-Coder-V2-Instruct

Similar models

Browse all →

More from gaianet

All by gaianet →

More DeepSeek models

All DeepSeek →

Other large models

All large models →