GO

Golem 70B v1a

GolemGGUF by NaphulaUpdated 2025-11-11
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant43.9 GB
Quick answer

Golem 70B v1a needs about 47.1 GB of memory at Q4_K_M (a 43.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 43.9 GB (Q4_K_M) to 62.8 GB (Q6_K).

Golem 70B v1a is a 70.6B-parameter Golem model in GGUF format, quantized by Naphula. Its trained context length is 8K tokens. The repository has 2 quant files, from 43.9 GB (Q4_K_M) to 62.8 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M43.9 GB 47.1 GB
Too big Get file →
Q6_K62.8 GB (2 parts) 66.0 GB
Too big Get file →

What GPU do you need for Golem 70B v1a?

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 (43.9 GB file, about 47.1 GB in use).

Which Golem 70B v1a quant should you choose?

Q4_K_M is the usual starting point for Golem 70B v1a: it balances file size and quality well. Here it is a 43.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized byNaphula
FamilyGolem
Downloads (HF)2
Last updated2025-11-11

Frequently asked questions about Golem 70B v1a

How much VRAM does Golem 70B v1a need?

About 47.1 GB at Q4_K_M with an 8K context window. That is the 43.9 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 Golem 70B v1a on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 47.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Golem 70B v1a GGUF?

It depends on the quant: Q4_K_M is 43.9 GB, Q6_K is 62.8 GB.

What context length does Golem 70B v1a support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Golem 70B v1a GGUF?

The files are on Hugging Face in the Naphula/Golem-70B-v1a-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Naphula

All by Naphula →

More Golem models

All Golem →

Other large models

All large models →