GO

GodziLLa2 70B

GodzillaGGUF by TheBlokeUpdated 2023-11-14
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

GodziLLa2 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).

GodziLLa2 70B – a 70B‑parameter LLaMA‑based model in GGUF format

GodziLLa2 70B is a 69‑billion‑parameter LLaMA model released by MayaPH and quantized by TheBloke. It supports a 4096‑token context window and is licensed under llama2. The model is available in multiple GGUF quantisations for CPU and GPU inference.

Good at

  • Large‑scale instruction following
  • Multitask reasoning
  • High‑capacity context handling

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License restricts commercial use

Best for

  • Research benchmarking
  • LLM stress testing
  • Instruction‑driven applications

Who it’s for. Researchers and developers needing a large LLaMA‑based model for experimentation and benchmarking. The model is suitable for those who can manage the memory requirements and comply with the llama2 license.

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 Q2_K (file size 29.28 GB, estimated 32.5 GB memory). For 16 GB VRAM, Q3_K_S (29.92 GB, 33.1 GB memory) or Q4_0 (38.87 GB, 42.1 GB memory). For 24 GB VRAM, Q5_0 (47.46 GB, 50.6 GB memory) or Q5_K_M (48.75 GB, 51.9 GB memory). Estimates are approximate.

What GPU do you need for GodziLLa2 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 GodziLLa2 70B quant should you choose?

Q4_K_M is the usual starting point for GodziLLa2 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
FamilyGodzilla
Licensellama2
Downloads (HF)717
Last updated2023-11-14

Frequently asked questions about GodziLLa2 70B

How much VRAM does GodziLLa2 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 GodziLLa2 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 GodziLLa2 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 GodziLLa2 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 GodziLLa2 70B GGUF?

The files are on Hugging Face in the TheBloke/GodziLLa2-70B-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 GodziLLa2 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 GodziLLa2 70B on 8 GB VRAM?

Use the Q2_K quant, which requires about 32.5 GB of VRAM at 8 k context. 8 GB VRAM is insufficient.

Does the model support image inputs?

No, GodziLLa2 70B has no vision capability.

What license applies to this model?

The model is licensed under llama2.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Godzilla models

All Godzilla →

Other large models

All large models →