MI

Changgil K2S3 Mistral 7b v1.3

MistralGGUF by RichardErkhovUpdated 2024-06-26
Download on Hugging Face
Parameters7.37B
Context32K
Layers—
Architecturellama
Smallest quant2.8 GB
Quick answer

Changgil K2S3 Mistral 7b v1.3 needs about 3.6 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 2.8 GB (Q2_K) to 6.2 GB (Q8_0).

Changgil K2S3 Mistral 7b v1.3 is a 7.37B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 2.8 GB (Q2_K) to 6.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 3.6 GB
Fits Get file →
Q4_K_M2.8 GB 3.6 GB
Fits Get file →
IQ3_XS3.1 GB 4.0 GB
Fits Get file →
Q3_K_S3.2 GB 4.1 GB
Fits Get file →
IQ3_S3.3 GB 4.2 GB
Fits Get file →
Q4_13.4 GB 4.3 GB
Fits Get file →
IQ3_M3.4 GB 4.3 GB
Fits Get file →
Q3_K3.6 GB 4.5 GB
Fits Get file →
Q3_K_M3.6 GB 4.5 GB
Fits Get file →
Q3_K_L3.9 GB 4.9 GB
Fits Get file →
IQ4_XS4.0 GB 5.0 GB
Fits Get file →
Q4_04.2 GB 5.2 GB
Fits Get file →
Q4_K_S4.2 GB 5.2 GB
Fits Get file →
IQ4_NL4.2 GB 5.3 GB
Fits Get file →
Q4_K4.5 GB 5.5 GB
Fits Get file →
Q5_05.1 GB 6.2 GB
Fits Get file →
Q5_K_S5.1 GB 6.2 GB
Fits Get file →
Q5_K5.2 GB 6.4 GB
Fits Get file →
Q5_K_M5.2 GB 6.4 GB
Fits Get file →
Q5_15.5 GB 6.7 GB
Fits Get file →
Q6_K6.0 GB 7.3 GB
Tight Get file →
Q8_06.2 GB 7.4 GB
Tight Get file →

What GPU do you need for Changgil K2S3 Mistral 7b v1.3?

These figures add the file size, an fp16 KV cache at an 8K context window 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 IQ3_XS (3.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K (4.5 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (6.2 GB file, about 7.4 GB in use).

Which Changgil K2S3 Mistral 7b v1.3 quant should you choose?

Q4_K_M is the usual starting point for Changgil K2S3 Mistral 7b v1.3: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 6.2 GB, about 2.2 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 2.8 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
Parameters7.37B
Trained context32,768 tokens

Source

Quantized byRichardErkhov
FamilyMistral
Downloads (HF)64
Last updated2024-06-26

Frequently asked questions about Changgil K2S3 Mistral 7b v1.3

How much VRAM does Changgil K2S3 Mistral 7b v1.3 need?

About 3.6 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Changgil K2S3 Mistral 7b v1.3 on an 8 GB GPU?

Yes, with Q8_0: the 6.2 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Changgil K2S3 Mistral 7b v1.3 GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q4_K_M is 2.8 GB, IQ3_XS is 3.1 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.3 GB, Q4_1 is 3.4 GB and 16 more.

What context length does Changgil K2S3 Mistral 7b v1.3 support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download Changgil K2S3 Mistral 7b v1.3 GGUF?

The files are on Hugging Face in the RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.3-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other small models

All small models →