DO

Dolphin 2.1 70B

DolphinGGUF by TheBlokeUpdated 2023-10-25
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

Dolphin 2.1 70B needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M).

Dolphin 2.1 70B – a large, uncensored LLM in GGUF format

Dolphin 2.1 70B is a 69‑billion‑parameter llama‑based model. It is released in GGUF format and supports the ChatML prompt format. The model is uncensored and requires a custom alignment layer for responsible deployment.

Good at

  • Chat‑style dialogue
  • Creative writing
  • Technical explanations

Limits

  • Bug prevents EOS token generation
  • Requires special word to signal end
  • No vision support

Best for

  • Developers building chatbots
  • Researchers testing large‑scale LLMs
  • Content creators needing detailed responses

Who it’s for. This model is suitable for both commercial and non‑commercial use under the llama2 license. It is ideal for users who need a large, uncensored model and are prepared to handle the EOS bug and alignment concerns.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.3 GB 31.1 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_M33.2 GB 35.0 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
Q4_038.9 GB 40.7 GB
Too big Get file →
Q4_K_S39.1 GB 40.9 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_047.5 GB 49.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 41.42 GB, estimated 44.6 GB memory). For 16 GB VRAM, Q4_K_S (39.07 GB, 42.3 GB memory) or Q3_K_M (33.19 GB, 36.4 GB memory) are good options. Higher‑bit quants like Q5_K_M provide better quality but need more memory.

What GPU do you need for Dolphin 2.1 70B?

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: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which Dolphin 2.1 70B quant should you choose?

Q4_K_M is the usual starting point for Dolphin 2.1 70B: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.3 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyDolphin
Licensellama2
Downloads (HF)1,748
Last updated2023-10-25

Frequently asked questions about Dolphin 2.1 70B

How much VRAM does Dolphin 2.1 70B need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Dolphin 2.1 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dolphin 2.1 70B GGUF?

It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.1 GB and 4 more.

What context length does Dolphin 2.1 70B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Dolphin 2.1 70B GGUF?

The files are on Hugging Face in the TheBloke/Dolphin-2.1-70B-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 Dolphin 2.1 70B use?

Hugging Face lists the license as llama2. 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 Dolphin 2.1 70B on 8 GB VRAM?

Use the Q4_K_M quant; it requires about 44.6 GB memory at 8 k context, which exceeds 8 GB VRAM. A lower‑bit quant is needed for 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the EOS token issue?

The model cannot generate EOS tokens; instruct it to say a special word to signal completion.

Other GGUFs of dolphin-2.1-70b

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Dolphin models

All Dolphin →

Other large models

All large models →