SY

Synthia 70B

SynthiaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters69B
Context—
Layers—
Architecture—
Smallest quant29.1 GB
Quick answer

Synthia 70B needs about 46.8 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 8 quants, from 29.1 GB (Q2_K) to 48.8 GB (Q5_K_M).

Synthia 70B – a 70B parameter Llama‑2 fine‑tuned for instruction following

Synthia 70B is a 69 billion parameter model based on Llama‑2. It is fine‑tuned on Orca style datasets for instruction following and long‑form conversation. The model is available in GGUF format and can be run with llama.cpp and compatible clients.

Good at

  • Instruction following
  • Long‑form conversation
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License bound to llama2

Best for

  • Chatbots needing detailed responses
  • Content generation with extended context
  • Research prototyping on local hardware

Who it’s for. Developers and researchers who need a large language model for local inference. The model is suitable for users with sufficient GPU memory and who comply with the llama2 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.1 GB 33.1 GB
Too big Get file →
Q3_K_S29.7 GB 33.8 GB
Too big Get file →
Q3_K_M33.1 GB 37.6 GB
Too big Get file →
Q3_K_L36.1 GB 41.0 GB
Too big Get file →
Q4_K_S39.0 GB 44.2 GB
Too big Get file →
Q4_K_M41.4 GB 46.8 GB
Too big Get file →
Q5_K_S47.5 GB 53.7 GB
Too big Get file →
Q5_K_M48.8 GB 55.1 GB
Too big Get file →

For 8 GB VRAM use Q2_K (29.11 GB file, 33.1 GB memory at 8k). For 12 GB VRAM use Q3_K_S (29.75 GB file, 33.8 GB memory). For 16 GB VRAM use Q4_K_S (38.99 GB file, 44.2 GB memory). Estimates are approximate.

What GPU do you need for Synthia 70B?

These figures add the file size, an fp16 KV cache at an 8K context window 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 46.8 GB in use).

Which Synthia 70B quant should you choose?

Q4_K_M is the usual starting point for Synthia 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 29.1 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

Parameters69B

Source

Quantized byTheBloke
FamilySynthia
Licensellama2
Downloads (HF)1,034
Last updated2023-09-27

Frequently asked questions about Synthia 70B

How much VRAM does Synthia 70B need?

About 46.8 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 Synthia 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Synthia 70B GGUF?

It depends on the quant: Q2_K is 29.1 GB, Q3_K_S is 29.7 GB, Q3_K_M is 33.1 GB, Q3_K_L is 36.1 GB, Q4_K_S is 39.0 GB, Q4_K_M is 41.4 GB and 2 more.

Where can I download Synthia 70B GGUF?

The files are on Hugging Face in the TheBloke/Synthia-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 Synthia 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 Synthia 70B on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 33.1 GB of VRAM at 8k context.

Does Synthia 70B support image input?

No, the model has no vision capabilities.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

Other large models

All large models →