LL

Slim Llama3.1 405B

LlamaGGUF by mradermacherUpdated 2025-12-08
Download on Hugging Face
Parameters71.1B
Context128K
Layers21
Architecturellama
Smallest quant26.9 GB
Quick answer

Slim Llama3.1 405B needs about 44.1 GB of memory at Q4_K_M (a 42.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 26.9 GB (Q2_K) to 75.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Slim Llama3.1 405B is a 71.1B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 11 quant files, from 26.9 GB (Q2_K) to 75.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.9 GB 28.1 GB
Too big Get file →
Q3_K_S31.4 GB 32.6 GB
Too big Get file →
Q3_K_M34.7 GB 35.9 GB
Too big Get file →
Q3_K_L37.7 GB 38.9 GB
Too big Get file →
IQ4_XS38.7 GB 39.9 GB
Too big Get file →
Q4_K_S40.8 GB 42.0 GB
Too big Get file →
Q4_K_M42.9 GB 44.1 GB
Too big Get file →
Q5_K_S49.2 GB 50.4 GB
Too big Get file →
Q5_K_M50.4 GB 51.6 GB
Too big Get file →
Q6_K58.4 GB 59.6 GB
Too big Get file →
Q8_075.6 GB 76.8 GB
Too big Get file →

What GPU do you need for Slim Llama3.1 405B?

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: the best quant that fits is Q2_K (26.9 GB file, about 28.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.9 GB file, about 44.1 GB in use).

Which Slim Llama3.1 405B quant should you choose?

Q4_K_M is the usual starting point for Slim Llama3.1 405B: it balances file size and quality well. Here it is a 42.9 GB file.

The Q8_0 file is 75.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 26.9 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
Parameters71.1B
Layers21
Trained context131,072 tokens
KV cache (fp16)84 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)140
Last updated2025-12-08

Frequently asked questions about Slim Llama3.1 405B

How much VRAM does Slim Llama3.1 405B need?

About 44.1 GB at Q4_K_M with an 8K context window. That is the 42.9 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 Slim Llama3.1 405B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Slim Llama3.1 405B GGUF?

It depends on the quant: Q2_K is 26.9 GB, Q3_K_S is 31.4 GB, Q3_K_M is 34.7 GB, Q3_K_L is 37.7 GB, IQ4_XS is 38.7 GB, Q4_K_S is 40.8 GB and 5 more.

What context length does Slim Llama3.1 405B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download Slim Llama3.1 405B GGUF?

The files are on Hugging Face in the mradermacher/Slim-Llama3.1-405B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Slim-Llama3.1-405B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →