MA

Mathstral 7B v0.1 Fp16

MathstralGGUF by DiluzxUpdated 2024-07-19
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant29.0 GB
Quick answer

Mathstral 7B v0.1 Fp16 needs about 30.6 GB of memory at F32 (a 29.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mathstral 7B v0.1 Fp16 is a 7.25B-parameter Mathstral model in GGUF format, quantized by Diluzx. Its trained context length is 32K tokens. The repository has 1 quant file, from 29.0 GB (F32) to 29.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F3229.0 GB 30.6 GB
Too big Get file →

What GPU do you need for Mathstral 7B v0.1 Fp16?

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 F32 (29.0 GB file, about 30.6 GB in use).

Which Mathstral 7B v0.1 Fp16 quant should you choose?

F32 (29.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byDiluzx
FamilyMathstral
Licenseapache-2.0
Downloads (HF)23
Last updated2024-07-19

Frequently asked questions about Mathstral 7B v0.1 Fp16

How much VRAM does Mathstral 7B v0.1 Fp16 need?

About 30.6 GB at F32 with an 8K context window. That is the 29.0 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 Mathstral 7B v0.1 Fp16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mathstral 7B v0.1 Fp16 GGUF?

It depends on the quant: F32 is 29.0 GB.

What context length does Mathstral 7B v0.1 Fp16 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Mathstral 7B v0.1 Fp16 GGUF?

The files are on Hugging Face in the Diluzx/mathstral-7B-v0.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mathstral 7B v0.1 Fp16 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from Diluzx

All by Diluzx →

More Mathstral models

All Mathstral →

Other small models

All small models →