SY

Synthia 70B v1.1 i1

SynthiaGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters69B
Context2K
Layers80
Architecturellama
Smallest quant14.9 GB
Quick answer

Synthia 70B v1.1 i1 needs about 44.9 GB of memory at Q4_K_M (a 41.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 17 quants, from 14.9 GB (IQ1_S) to 49.1 GB (Q5_K_M).

Synthia 70B v1.1 i1 – a large llama-based model in GGUF format

Synthia 70B v1.1 i1 is a 69‑billion‑parameter llama model released under the llama2 license. It supports a 2048‑token context window and is available in multiple quantized GGUF files. The model is suitable for general-purpose text generation and analysis.

Good at

  • Large‑scale text generation
  • Contextual reasoning
  • Multilingual support

Limits

  • No vision capabilities
  • Requires high VRAM for larger quants
  • License restricts commercial use

Best for

  • Research prototyping
  • Fine‑tuning experiments
  • Content creation

Who it’s for. Developers and researchers who need a powerful text model in a lightweight GGUF format. The model is ideal for those who can manage the memory requirements and comply with the llama2 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.9 GB 16.1 GB
Too big Get file →
IQ2_XXS18.6 GB 19.8 GB
Too big Get file →
IQ2_XS20.7 GB 21.8 GB
Too big Get file →
IQ2_S21.7 GB 22.9 GB
Too big Get file →
IQ2_M23.6 GB 24.7 GB
Too big Get file →
Q2_K25.8 GB 26.9 GB
Too big Get file →
IQ3_XXS26.9 GB 28.1 GB
Too big Get file →
IQ3_XS28.5 GB 29.6 GB
Too big Get file →
IQ3_S30.2 GB 31.4 GB
Too big Get file →
Q3_K_S30.2 GB 31.4 GB
Too big Get file →
IQ3_M31.3 GB 32.4 GB
Too big Get file →
Q3_K_M33.6 GB 34.8 GB
Too big Get file →
Q3_K_L36.5 GB 37.6 GB
Too big Get file →
Q4_K_S39.6 GB 40.7 GB
Too big Get file →
Q4_K_M41.7 GB 42.9 GB
Too big Get file →
Q5_K_S47.8 GB 48.9 GB
Too big Get file →
Q5_K_M49.1 GB 50.2 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (14.88 GB file, 18.1 GB memory). With 12 GB VRAM IQ2_XXS (18.63 GB file, 21.8 GB memory) is suitable. If 16 GB VRAM is available, IQ2_S (21.7 GB file, 24.9 GB memory) offers a good balance of size and performance.

What GPU do you need for Synthia 70B v1.1 i1?

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: the best quant that fits is IQ2_XS (20.7 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.5 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.7 GB file, about 44.9 GB in use).

Which Synthia 70B v1.1 i1 quant should you choose?

Q4_K_M is the usual starting point for Synthia 70B v1.1 i1: it balances file size and quality well. Here it is a 41.7 GB file.

If memory is tight, the smallest file is IQ1_S at 14.9 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

Architecturellama
Parameters69B
Layers80
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilySynthia
Licensellama2
Downloads (HF)1,148
Last updated2024-05-06

Frequently asked questions about Synthia 70B v1.1 i1

How much VRAM does Synthia 70B v1.1 i1 need?

About 44.9 GB at Q4_K_M with an 8K context window. That is the 41.7 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 v1.1 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Synthia 70B v1.1 i1 GGUF?

It depends on the quant: IQ1_S is 14.9 GB, IQ2_XXS is 18.6 GB, IQ2_XS is 20.7 GB, IQ2_S is 21.7 GB, IQ2_M is 23.6 GB, Q2_K is 25.8 GB and 11 more.

What context length does Synthia 70B v1.1 i1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download Synthia 70B v1.1 i1 GGUF?

The files are on Hugging Face in the mradermacher/Synthia-70B-v1.1-i1-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 v1.1 i1 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 v1.1 i1 on 8 GB VRAM?

Yes, the IQ1_S quant uses 14.88 GB file size and requires approximately 18.1 GB VRAM at 8 k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the llama2 license.

Other GGUFs of SynthIA-70B-v1.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Synthia models

All Synthia →

Other large models

All large models →