MI

K2S3 Mistral 7b v1.46

MistralGGUF by RichardErkhovUpdated 2024-09-18
Download on Hugging Face
Parameters7.37B
Context32K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

K2S3 Mistral 7b v1.46 needs about 6.0 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 2.8 GB (Q2_K) to 7.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

K2S3 Mistral 7b v1.46 – a 7.37B parameter Llama‑style model

K2S3 Mistral 7b v1.46 is a 7.37B parameter model based on Mistral‑7B‑v0.1. It was fine‑tuned with full‑parameter SFT on alpaca‑gpt4‑data and OpenOrca samples. The model supports a context length of 32768 tokens and is released under cc‑by‑nc‑4.0.

Good at

  • Fine‑tuned on instruction data
  • Supports 32768‑token context
  • Available in multiple GGUF quantizations

Limits

  • No vision support
  • cc‑by‑nc‑4.0 license
  • Requires GPU for inference

Best for

  • Instruction following tasks
  • Long‑form text generation
  • Chatbot back‑end

Who it’s for. Developers building LLM‑powered applications who need a large‑context model and can comply with a non‑commercial license. The model is suitable for research and internal tooling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.2 GB 4.8 GB
Fits Get file →
IQ3_S3.3 GB 4.8 GB
Fits Get file →
IQ3_M3.4 GB 4.9 GB
Fits Get file →
Q3_K3.6 GB 5.2 GB
Fits Get file →
Q3_K_M3.6 GB 5.2 GB
Fits Get file →
Q3_K_L3.9 GB 5.5 GB
Fits Get file →
IQ4_XS4.0 GB 5.6 GB
Fits Get file →
Q4_04.2 GB 5.8 GB
Fits Get file →
Q4_K_S4.2 GB 5.8 GB
Fits Get file →
IQ4_NL4.2 GB 5.8 GB
Fits Get file →
Q4_K4.5 GB 6.0 GB
Fits Get file →
Q4_K_M4.5 GB 6.0 GB
Fits Get file →
Q4_14.6 GB 6.2 GB
Fits Get file →
Q5_05.1 GB 6.7 GB
Fits Get file →
Q5_K_S5.1 GB 6.7 GB
Fits Get file →
Q5_K5.2 GB 6.8 GB
Fits Get file →
Q5_K_M5.2 GB 6.8 GB
Fits Get file →
Q5_15.5 GB 7.1 GB
Fits Get file →
Q6_K6.0 GB 7.6 GB
Tight Get file →
Q8_07.8 GB 9.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 4.2 GB, memory 5.8 GB). For 12 GB VRAM, Q4_K (4.46 GB, 6 GB). For 16 GB VRAM, Q5_0 (5.1 GB, 6.7 GB). Memory estimates are approximate.

What GPU do you need for K2S3 Mistral 7b v1.46?

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: the best quant that fits is Q4_K (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 9.4 GB in use).

Which K2S3 Mistral 7b v1.46 quant should you choose?

Q4_K_M is the usual starting point for K2S3 Mistral 7b v1.46: it balances file size and quality well. Here it is a 4.5 GB file.

The Q8_0 file is 7.8 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 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
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Downloads (HF)1,927
Last updated2024-09-18

Frequently asked questions about K2S3 Mistral 7b v1.46

How much VRAM does K2S3 Mistral 7b v1.46 need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 4.5 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 K2S3 Mistral 7b v1.46 on an 8 GB GPU?

Yes, with Q6_K: the 6.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of K2S3 Mistral 7b v1.46 GGUF?

It depends on the quant: Q2_K is 2.8 GB, IQ3_XS is 3.1 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.3 GB, IQ3_M is 3.4 GB, Q3_K is 3.6 GB and 16 more.

What context length does K2S3 Mistral 7b v1.46 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 K2S3 Mistral 7b v1.46 GGUF?

The files are on Hugging Face in the RichardErkhov/Changgil_-_K2S3-Mistral-7b-v1.46-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 K2S3 Mistral 7b v1.46 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 K2S3 Mistral 7b v1.46 on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires about 5.8 GB of VRAM at 8 k context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under cc‑by‑nc‑4.0, allowing non‑commercial use with attribution.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other small models

All small models →