TR

Trendyol LLM 7b gguf v1.0

TrendyolGGUF by alperioxUpdated 2024-06-10
Download on Hugging Face
Parameters7.34B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

Trendyol LLM 7b gguf v1.0 needs about 6.0 GB of memory at F16 (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 4.4 GB (F16) to 14.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Trendyol LLM 7b gguf v1.0 is a 7.34B-parameter Trendyol model in GGUF format, quantized by alperiox. Its trained context length is 32K tokens. The repository has 3 quant files, from 4.4 GB (F16) to 14.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F164.4 GB 6.0 GB
Fits Get file →
F164.4 GB 6.0 GB
Fits Get file →
F1614.7 GB 16.3 GB
Too big Get file →

What GPU do you need for Trendyol LLM 7b gguf v1.0?

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 F16 (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (4.4 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (4.4 GB file, about 6.0 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (4.4 GB file, about 6.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.7 GB file, about 16.3 GB in use).

Which Trendyol LLM 7b gguf v1.0 quant should you choose?

F16 (4.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is F16 at 4.4 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.34B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byalperiox
FamilyTrendyol
Licenseapache-2.0
Downloads (HF)144
Last updated2024-06-10

Frequently asked questions about Trendyol LLM 7b gguf v1.0

How much VRAM does Trendyol LLM 7b gguf v1.0 need?

About 6.0 GB at F16 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 Trendyol LLM 7b gguf v1.0 on an 8 GB GPU?

Yes, with F16: the 4.4 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Trendyol LLM 7b gguf v1.0 GGUF?

It depends on the quant: F16 is 4.4 GB, F16 is 4.4 GB, F16 is 14.7 GB.

What context length does Trendyol LLM 7b gguf v1.0 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 Trendyol LLM 7b gguf v1.0 GGUF?

The files are on Hugging Face in the alperiox/Trendyol-LLM-7b-gguf-v1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Trendyol LLM 7b gguf v1.0 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Trendyol-LLM-7b-base-v1.0

Similar models

Browse all →

More from alperiox

All by alperiox →

More Trendyol models

All Trendyol →

Other small models

All small models →