BE

MS Beast 33b

BeastGGUF by mradermacherUpdated 2024-12-03
Download on Hugging Face
Parameters33.2B
Context32K
Layers84
Architecturellama
Smallest quant12.3 GB
Quick answer

MS Beast 33b needs about 23.2 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.3 GB (Q2_K) to 35.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.3 GB.

MS Beast 33b is a 33.2B-parameter Beast model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 11 quant files, from 12.3 GB (Q2_K) to 35.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.3 GB 15.6 GB
Too big Get file →
Q3_K_S14.3 GB 17.7 GB
Too big Get file →
Q3_K_M16.0 GB 19.3 GB
Too big Get file →
Q3_K_L17.5 GB 20.8 GB
Too big Get file →
IQ4_XS17.9 GB 21.2 GB
Too big Get file →
Q4_K_S18.8 GB 22.2 GB
Too big Get file →
Q4_K_M19.9 GB 23.2 GB
Too big Get file →
Q5_K_S22.8 GB 26.2 GB
Too big Get file →
Q5_K_M23.4 GB 26.8 GB
Too big Get file →
Q6_K27.2 GB 30.5 GB
Too big Get file →
Q8_035.2 GB 38.6 GB
Too big Get file →

What GPU do you need for MS Beast 33b?

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: the best quant that fits is Q2_K (12.3 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.9 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.2 GB file, about 30.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.2 GB file, about 38.6 GB in use).

Which MS Beast 33b quant should you choose?

Q4_K_M is the usual starting point for MS Beast 33b: it balances file size and quality well. Here it is a 19.9 GB file.

The Q8_0 file is 35.2 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 12.3 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
Parameters33.2B
Layers84
Trained context32,768 tokens
KV cache (fp16)336 KB per token

Source

Quantized bymradermacher
FamilyBeast
Downloads (HF)129
Last updated2024-12-03

Frequently asked questions about MS Beast 33b

How much VRAM does MS Beast 33b need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 19.9 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 MS Beast 33b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MS Beast 33b GGUF?

It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.3 GB, Q3_K_M is 16.0 GB, Q3_K_L is 17.5 GB, IQ4_XS is 17.9 GB, Q4_K_S is 18.8 GB and 5 more.

What context length does MS Beast 33b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.8 GB at 8K and 11.3 GB at 32K.

Where can I download MS Beast 33b GGUF?

The files are on Hugging Face in the mradermacher/MS-Beast-33b-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 MS-Beast-33b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Beast models

All Beast →

Other medium models

All medium models →