MI

NeuralHermes 2.5 Mistral 7B laser imatrix

MistralGGUF by BakanayatsuUpdated 2024-02-14
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

NeuralHermes 2.5 Mistral 7B laser imatrix needs about 4.5 GB of memory at IQ3_XXS (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 6 quants, from 2.0 GB (IQ2_XXS) to 7.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

NeuralHermes 2.5 Mistral 7B laser imatrix – 7.24B parameter LLM with tool use

NeuralHermes 2.5 Mistral 7B laser imatrix is a 7.24B parameter model built on the Mistral architecture. It supports tool use and has a 32768 token context window. The model is available in multiple GGUF quantizations.

Good at

  • Tool integration
  • Long context handling
  • Mistral architecture performance

Limits

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

Best for

  • Developers building tool‑enabled assistants
  • Researchers needing long‑context models
  • Applications requiring Mistral performance

Who it’s for. This model is suited for developers and researchers who need a 7B parameter LLM with tool‑use capability and a large context window. It is ideal for building assistants that interact with external APIs or services.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ3_XXS2.9 GB 4.5 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
—7.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM use IQ2_XXS (1.99 GB, 3.6 GB memory at 8K context) or IQ2_XS (2.2 GB, 3.8 GB memory). For 12 GB VRAM use Q4_K_S (4.14 GB, 5.7 GB memory) or Q5_K_S (5 GB, 6.6 GB memory). Higher quants need more VRAM.

What GPU do you need for NeuralHermes 2.5 Mistral 7B laser imatrix?

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_S (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (5.0 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).

Which NeuralHermes 2.5 Mistral 7B laser imatrix quant should you choose?

IQ3_XXS (2.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_XXS at 2.0 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byBakanayatsu
FamilyMistral
Downloads (HF)770
Last updated2024-02-14

Frequently asked questions about NeuralHermes 2.5 Mistral 7B laser imatrix

How much VRAM does NeuralHermes 2.5 Mistral 7B laser imatrix need?

About 4.5 GB at IQ3_XXS with an 8K context window. That is the 2.9 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 NeuralHermes 2.5 Mistral 7B laser imatrix on an 8 GB GPU?

Yes, with Q5_K_S: the 5.0 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NeuralHermes 2.5 Mistral 7B laser imatrix GGUF?

It depends on the quant: IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ3_XXS is 2.9 GB, Q4_K_S is 4.1 GB, Q5_K_S is 5.0 GB, file is 7.7 GB.

What context length does NeuralHermes 2.5 Mistral 7B laser imatrix 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 NeuralHermes 2.5 Mistral 7B laser imatrix GGUF?

The files are on Hugging Face in the Bakanayatsu/NeuralHermes-2.5-Mistral-7B-laser-imatrix-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 NeuralHermes 2.5 on 8 GB VRAM?

Yes, use IQ2_XXS or IQ2_XS quantizations; they require approximately 3.6–3.8 GB memory at 8K context.

Does this model support vision?

No, the model does not have vision capabilities.

What is the context length of this model?

The model supports a context length of 32768 tokens.

Similar models

Browse all →

More from Bakanayatsu

All by Bakanayatsu →

More Mistral models

All Mistral →

Other small models

All small models →