DE

deepseek llm 67b chat

DeepSeekGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters67.4B
Context4K
Layers95
Architecturellama
Smallest quant25.1 GB
Quick answer

deepseek llm 67b chat needs about 44.1 GB of memory at Q4_K_M (a 40.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.1 GB (Q2_K) to 47.7 GB (Q5_K_M).

DeepSeek LLM 67B Chat – 67.4B parameter Llama‑style chat model

DeepSeek LLM 67B Chat is a 67.4B parameter model fine‑tuned for chat from a 67B base. It supports 4096 token context and is available in multiple GGUF quantizations. The model is licensed under MIT with a separate model license allowing commercial use.

Good at

  • Large context chat
  • High‑parameter language understanding
  • Fine‑tuned instruction following

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License requires model license compliance

Best for

  • Research on large‑scale chat models
  • Testing quantization effects
  • Deploying chatbots on high‑memory GPUs

Who it’s for. Researchers and developers needing a 67B chat model with open‑source access. The model is suitable for experimentation and commercial deployment under the provided licenses.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.1 GB 27.2 GB
Too big Get file →
IQ3_XS27.9 GB 30.0 GB
Too big Get file →
Q3_K_S29.3 GB 31.4 GB
Too big Get file →
IQ3_S29.4 GB 31.5 GB
Too big Get file →
IQ3_M30.5 GB 32.6 GB
Too big Get file →
Q3_K_M32.7 GB 34.7 GB
Too big Get file →
Q3_K_L35.6 GB 37.7 GB
Too big Get file →
IQ4_XS36.5 GB 38.6 GB
Too big Get file →
Q4_K_S38.4 GB 40.5 GB
Too big Get file →
Q4_K_M40.4 GB 42.5 GB
Too big Get file →
Q5_K_S46.5 GB 48.6 GB
Too big Get file →
Q5_K_M47.7 GB 49.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (25.12 GB file, ~28.8 GB memory). For 16 GB VRAM, Q3_K_S (29.31 GB file, ~33 GB memory) or IQ3_S (29.42 GB file, ~33.1 GB memory). For 24 GB VRAM, Q4_K_M (40.44 GB file, ~44.1 GB memory) or Q5_K_S (46.48 GB file, ~50.2 GB memory). Estimates are approximate.

What GPU do you need for deepseek llm 67b 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: 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: the best quant that fits is IQ3_XS (27.9 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (40.4 GB file, about 44.1 GB in use).

Which deepseek llm 67b chat quant should you choose?

Q4_K_M is the usual starting point for deepseek llm 67b chat: it balances file size and quality well. Here it is a 40.4 GB file.

If memory is tight, the smallest file is Q2_K at 25.1 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

Architecturellama
Parameters67.4B
Layers95
Trained context4,096 tokens
KV cache (fp16)380 KB per token

Source

Quantized bymradermacher
FamilyDeepSeek
Licenseother
Downloads (HF)1,206
Last updated2024-05-06

Frequently asked questions about deepseek llm 67b chat

How much VRAM does deepseek llm 67b chat need?

About 44.1 GB at Q4_K_M with an 8K context window. That is the 40.4 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 llm 67b chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of deepseek llm 67b chat GGUF?

It depends on the quant: Q2_K is 25.1 GB, IQ3_XS is 27.9 GB, Q3_K_S is 29.3 GB, IQ3_S is 29.4 GB, IQ3_M is 30.5 GB, Q3_K_M is 32.7 GB and 6 more.

What context length does deepseek llm 67b chat support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download deepseek llm 67b chat GGUF?

The files are on Hugging Face in the mradermacher/deepseek-llm-67b-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 llm 67b 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 LLM 67B Chat on 8 GB VRAM?

Only with the Q2_K quant, which requires about 28.8 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support vision tasks?

No, the model has no vision capabilities.

Is commercial use allowed?

Yes, the model license permits commercial use under the MIT license.

Other GGUFs of deepseek-llm-67b-chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More DeepSeek models

All DeepSeek →

Other large models

All large models →