MI

models--mistralai--mathstral-7B-v0.1

MistralGGUF by MaziyarPanahiUpdated 2024-07-16
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

models--mistralai--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 16 quants, from 1.6 GB (IQ1_S) to 14.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mathstral‑7B‑v0.1 – a 7 B model focused on math and science tasks

Mathstral‑7B‑v0.1 is a 7 B parameter model based on Mistral 7B. It specializes in mathematical and scientific reasoning. The model supports a 32 768 token context window.

Good at

  • Mathematical problem solving
  • Scientific reasoning
  • Long‑form technical explanations

Limits

  • No vision support
  • License not specified
  • Large VRAM required for higher quants

Best for

  • Solving algebraic equations
  • Explaining scientific concepts
  • Generating technical documentation

Who it’s for. Developers and researchers needing a local model for math and science tasks. It is suitable for use in llama.cpp, llama‑cpp‑python, or other GGUF‑compatible clients.

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_XS2.2 GB 3.8 GB
Fits Get file →
Q2_K2.7 GB 4.3 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 →
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_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 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 →
—14.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (1.62 GB) or IQ1_M (1.76 GB). For 12 GB VRAM use Q2_K (2.72 GB) or Q3_K_S (3.17 GB). For 16 GB VRAM use Q4_K_M (4.37 GB) or Q5_K_S (5 GB). Memory estimates are approximate.

What GPU do you need for models--mistralai--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_XS (2.2 GB file, about 3.8 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).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (14.5 GB file, about 16.1 GB in use).

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

Q4_K_M is the usual starting point for models--mistralai--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 byMaziyarPanahi
FamilyMistral
Downloads (HF)41,414
Last updated2024-07-16

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

How much VRAM does models--mistralai--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 models--mistralai--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 models--mistralai--mathstral-7B-v0.1 GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XS is 2.2 GB, Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB and 10 more.

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

The files are on Hugging Face in the MaziyarPanahi/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.

Can I run Mathstral‑7B‑v0.1 on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quant, which require about 3.2–3.3 GB of VRAM at 8 k context.

Does Mathstral‑7B‑v0.1 support image input?

No, the model has no vision capability.

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

It supports up to 32,768 tokens.

Other GGUFs of Mathstral-7B-v0.1

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Mistral models

All Mistral →

Other small models

All small models →