HI

HiTZ GoLLIE 13B AsSafeTensors i1

HitzGGUF by mradermacherUpdated 2025-03-02
Download on Hugging Face
Parameters13B
Context16K
Layers40
Architecturellama
Smallest quant2.9 GB
Quick answer

HiTZ GoLLIE 13B AsSafeTensors i1 needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 2.9 GB (IQ1_S) to 10.7 GB (Q6_K).

HiTZ GoLLIE 13B – a 13B Llama-based model for guideline‑following information extraction

HiTZ GoLLIE 13B is a 13B parameter Llama model fine‑tuned for following annotation guidelines in information extraction tasks. It is released under the llama2 license and supports English text generation. The model is available in multiple GGUF quantizations.

Good at

  • Guideline‑following extraction
  • Python class label generation
  • Zero‑shot information extraction

Limits

  • No vision support
  • Requires CUDA GPU for flash attention
  • Large VRAM needed for higher quants

Best for

  • Custom annotation schema inference
  • Jupyter notebook demos
  • Fine‑tuning with LoRA adapters

Who it’s for. Developers and researchers needing a text generation model that can follow detailed annotation guidelines. The model is suitable for building information extraction pipelines that require on‑the‑fly schema definition.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 10.1 GB
Too big Get file →
IQ1_M3.1 GB 10.3 GB
Too big Get file →
IQ2_XXS3.5 GB 10.7 GB
Too big Get file →
IQ2_XS3.9 GB 11.1 GB
Too big Get file →
IQ2_S4.2 GB 11.4 GB
Too big Get file →
Q2_K_S4.4 GB 11.6 GB
Too big Get file →
IQ2_M4.5 GB 11.7 GB
Too big Get file →
Q2_K4.9 GB 12.1 GB
Too big Get file →
IQ3_XXS5.0 GB 12.2 GB
Too big Get file →
IQ3_XS5.4 GB 12.6 GB
Too big Get file →
IQ3_S5.7 GB 12.9 GB
Too big Get file →
Q3_K_S5.7 GB 12.9 GB
Too big Get file →
IQ3_M6.0 GB 13.2 GB
Too big Get file →
Q3_K_M6.3 GB 13.5 GB
Too big Get file →
Q3_K_L6.9 GB 14.1 GB
Too big Get file →
IQ4_XS7.0 GB 14.2 GB
Too big Get file →
IQ4_NL7.4 GB 14.6 GB
Too big Get file →
Q4_07.4 GB 14.6 GB
Too big Get file →
Q4_K_S7.4 GB 14.6 GB
Too big Get file →
Q4_K_M7.9 GB 15.1 GB
Too big Get file →
Q4_18.2 GB 15.4 GB
Too big Get file →
Q5_K_S9.0 GB 16.2 GB
Too big Get file →
Q5_K_M9.2 GB 16.4 GB
Too big Get file →
Q6_K10.7 GB 17.9 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (2.9 GB, 10.1 GB memory at 8 k context) or IQ1_M (3.14 GB, 10.3 GB). For 12 GB VRAM use Q2_K (4.85 GB, 12.1 GB) or Q3_K_M (6.34 GB, 13.5 GB). For 16 GB VRAM use Q5_K_S (8.97 GB, 16.2 GB) or Q5_K_M (9.23 GB, 16.4 GB).

What GPU do you need for HiTZ GoLLIE 13B AsSafeTensors i1?

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: the best quant that fits is IQ2_M (4.5 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (10.7 GB file, about 17.9 GB in use).

Which HiTZ GoLLIE 13B AsSafeTensors i1 quant should you choose?

Q4_K_M is the usual starting point for HiTZ GoLLIE 13B AsSafeTensors i1: it balances file size and quality well. Here it is a 7.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.9 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
Parameters13B
Layers40
Trained context16,384 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyHitz
Licensellama2
Downloads (HF)824
Last updated2025-03-02

Frequently asked questions about HiTZ GoLLIE 13B AsSafeTensors i1

How much VRAM does HiTZ GoLLIE 13B AsSafeTensors i1 need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 HiTZ GoLLIE 13B AsSafeTensors i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of HiTZ GoLLIE 13B AsSafeTensors i1 GGUF?

It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.2 GB, Q2_K_S is 4.4 GB and 18 more.

What context length does HiTZ GoLLIE 13B AsSafeTensors i1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 6.7 GB at 8K and 13.4 GB at 16K.

Where can I download HiTZ GoLLIE 13B AsSafeTensors i1 GGUF?

The files are on Hugging Face in the mradermacher/HiTZ-GoLLIE-13B-AsSafeTensors-i1-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 HiTZ GoLLIE 13B AsSafeTensors i1 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 HiTZ GoLLIE 13B on 8 GB VRAM?

Yes, the IQ1_S quant uses 2.9 GB file size and requires about 10.1 GB VRAM at 8 k context.

Does the model support vision tasks?

No, HiTZ GoLLIE 13B is a text‑only model and does not support vision.

What license applies to the model?

The base model is licensed under llama2; LoRA adapters are under Apache 2.0.

Other GGUFs of HiTZ-GoLLIE-13B-AsSafeTensors

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Hitz models

All Hitz →

Other medium models

All medium models →