VI

vihangd smartsolmix 4x10.7b v1

VihangdGGUF by RichardErkhovUpdated 2024-07-24
Download on Hugging Face
Parameters36.1B
Context4K
Layers48
Architecturellama
Smallest quant13.2 GB
Quick answer

vihangd smartsolmix 4x10.7b v1 needs about 17.7 GB of memory at IQ3_S (a 15.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 13.2 GB (Q2_K) to 18.7 GB (Q3_K_L).

vihangd smartsolmix 4x10.7b v1 is a 36.1B-parameter Vihangd model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 8 quant files, from 13.2 GB (Q2_K) to 18.7 GB (Q3_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.2 GB 14.5 GB
Too big Get file →
IQ3_XS14.8 GB 16.1 GB
Too big Get file →
Q3_K_S15.6 GB 16.9 GB
Too big Get file →
IQ3_S15.6 GB 16.9 GB
Too big Get file →
IQ3_M15.9 GB 17.2 GB
Too big Get file →
Q3_K17.3 GB 18.6 GB
Too big Get file →
Q3_K_M17.3 GB 18.6 GB
Too big Get file →
Q3_K_L18.7 GB 20.0 GB
Too big Get file →

What GPU do you need for vihangd smartsolmix 4x10.7b v1?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q2_K (13.2 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_L (18.7 GB file, about 20.8 GB in use).

Which vihangd smartsolmix 4x10.7b v1 quant should you choose?

IQ3_S (15.6 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 Q2_K at 13.2 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
Parameters36.1B (approximate, mixture of experts)
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byRichardErkhov
FamilyVihangd
Licensecc-by-4.0
Downloads (HF)5
Last updated2024-07-24

Frequently asked questions about vihangd smartsolmix 4x10.7b v1

How much VRAM does vihangd smartsolmix 4x10.7b v1 need?

About 17.7 GB at IQ3_S with an 8K context window. That is the 15.6 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 vihangd smartsolmix 4x10.7b v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of vihangd smartsolmix 4x10.7b v1 GGUF?

It depends on the quant: Q2_K is 13.2 GB, IQ3_XS is 14.8 GB, Q3_K_S is 15.6 GB, IQ3_S is 15.6 GB, IQ3_M is 15.9 GB, Q3_K is 17.3 GB and 2 more.

What context length does vihangd smartsolmix 4x10.7b v1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download vihangd smartsolmix 4x10.7b v1 GGUF?

The files are on Hugging Face in the RichardErkhov/vihangd_-_smartsolmix-4x10.7b-v1-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 vihangd smartsolmix 4x10.7b v1 use?

Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

Other large models

All large models →