PU

PULI LlumiX 32K instruct

PuliGGUF by ariel-mlUpdated 2024-05-08
Download on Hugging Face
Parameters6.74B
Context32K
Layers32
Architecturellama
Smallest quant2.9 GB
Quick answer

PULI LlumiX 32K instruct needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 2.9 GB (Q3_K_S) to 7.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

PULI LlumiX 32K instruct – 6.74B param LLaMA‑2 based model

PULI LlumiX 32K instruct is a 6.74B parameter LLaMA‑2 model finetuned for Hungarian instruction following. It supports a 32 768 token context length and is available in multiple GGUF quantizations.

Good at

  • Hungarian instruction following
  • Long‑context reasoning up to 32 K tokens
  • ChatML prompt format

Limits

  • Requires 8 k context memory estimates 7.7–12 GB
  • No vision support
  • License: llama2

Best for

  • Chatbot in Hungarian
  • Long‑form content generation
  • Data analysis with extended context

Who it’s for. Developers and researchers needing a Hungarian‑focused instruction model with extended context. Suitable for local deployment via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_S (2.95 GB) or Q3_K_M (3.3 GB). For 12 GB VRAM, Q8_0 (7.16 GB) gives the highest quality. Memory estimates are approximate and based on 8 k context usage.

What GPU do you need for PULI LlumiX 32K instruct?

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: the best quant that fits is Q3_K_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which PULI LlumiX 32K instruct quant should you choose?

Q4_K_M is the usual starting point for PULI LlumiX 32K instruct: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 Q3_K_S at 2.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized byariel-ml
FamilyPuli
Licensellama2
Downloads (HF)628
Last updated2024-05-08

Frequently asked questions about PULI LlumiX 32K instruct

How much VRAM does PULI LlumiX 32K instruct need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 PULI LlumiX 32K instruct on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of PULI LlumiX 32K instruct GGUF?

It depends on the quant: Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q4_K_S is 3.9 GB, Q4_K_M is 4.1 GB, Q5_K_S is 4.7 GB, Q5_K_M is 4.8 GB and 2 more.

What context length does PULI LlumiX 32K instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download PULI LlumiX 32K instruct GGUF?

The files are on Hugging Face in the ariel-ml/PULI-LlumiX-32K-instruct-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 PULI LlumiX 32K instruct use?

Hugging Face lists the license as llama2. 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 PULI LlumiX 32K instruct on 8 GB VRAM?

Yes, use Q3_K_S or Q3_K_M quantizations which fit within 8 GB VRAM with approximate memory usage of 7.7–8.1 GB at 8 k context.

Does the model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What is the maximum context length?

The model supports a maximum sequence length of 32 768 tokens.

Similar models

Browse all →

More from ariel-ml

All by ariel-ml →

More Puli models

All Puli →

Other small models

All small models →