MA

mathstral-7B-v0.1

MathstralGGUF by mmngaUpdated 2024-07-17
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

mathstral-7B-v0.1 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.6 GB (IQ1_S) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mathstral 7B model for mathematical reasoning

mathstral-7B-v0.1 is a 7.25B parameter llama architecture model trained on 32768 context tokens. It is released under apache-2.0 and supports English and Japanese.

Good at

  • Mathematical problem solving
  • Logical reasoning
  • Code generation

Limits

  • No vision support
  • Requires large VRAM for higher quant
  • License allows free use

Best for

  • Academic tutoring
  • Research assistance
  • Programming help

Who it’s for. Developers and researchers needing a lightweight math‑focused LLM. The model is suitable for local deployment with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.8 GB 3.3 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
IQ4_NL4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (est. 3.2–3.3 GB). For 12 GB VRAM, IQ2_S or Q2_K (est. 3.9–4.3 GB). For 16 GB VRAM, Q3_K_M or Q4_K_M (est. 5.1–5.9 GB). Estimates are approximate.

What GPU do you need for mathstral-7B-v0.1?

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: the best quant that fits is IQ2_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which mathstral-7B-v0.1 quant should you choose?

Q4_K_M is the usual starting point for mathstral-7B-v0.1: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 IQ1_S at 1.6 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
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymmnga
FamilyMathstral
Licenseapache-2.0
Downloads (HF)1,599
Last updated2024-07-17

Frequently asked questions about mathstral-7B-v0.1

How much VRAM does mathstral-7B-v0.1 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 mathstral-7B-v0.1 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mathstral-7B-v0.1 GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 18 more.

What context length does mathstral-7B-v0.1 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 GGUF?

The files are on Hugging Face in the mmnga/mathstral-7B-v0.1-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 mathstral-7B-v0.1 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.

Can I run mathstral-7B-v0.1 on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM.

Does this model support Japanese language?

Yes, the model was trained with Japanese data and supports Japanese text.

Is the model free to use?

It is released under the apache-2.0 license, which allows free use and modification.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Mathstral models

All Mathstral →

Other small models

All small models →