HO

Holger 7B v0.1

HolgerGGUF by mradermacherUpdated 2024-11-13
Download on Hugging Face
Parameters7.55B
Context4K
Layers32
Architecturellama
Smallest quant1.9 GB
Quick answer

Holger 7B v0.1 needs about 9.4 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.9 GB (IQ1_S) to 6.2 GB (Q6_K).

Holger 7B v0.1 – a 7.55B parameter Llama model

Holger 7B v0.1 is a 7.55B parameter Llama model fine‑tuned on open data. It supports a 4096 token context window and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Fine‑tuned for Danish and other Scandinavian languages
  • Supports 4096 token context
  • Open source with permissive license

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No mixture of experts

Best for

  • Local inference on modest GPUs
  • Text generation in Scandinavian languages
  • Fine‑tuning with open data

Who it’s for. Developers and researchers who need a Danish‑friendly Llama model with a permissive license. The model is suitable for local deployment and further fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 4.6 GB
Fits Get file →
IQ1_M2.1 GB 4.7 GB
Fits Get file →
IQ2_XXS2.3 GB 4.9 GB
Fits Get file →
IQ2_XS2.5 GB 5.1 GB
Fits Get file →
IQ2_S2.7 GB 5.3 GB
Fits Get file →
IQ2_M2.8 GB 5.5 GB
Fits Get file →
Q2_K3.0 GB 5.7 GB
Fits Get file →
IQ3_XXS3.0 GB 5.7 GB
Fits Get file →
IQ3_XS3.3 GB 6.0 GB
Fits Get file →
IQ3_S3.5 GB 6.1 GB
Fits Get file →
Q3_K_S3.5 GB 6.1 GB
Fits Get file →
IQ3_M3.6 GB 6.3 GB
Fits Get file →
Q3_K_M3.8 GB 6.5 GB
Fits Get file →
Q3_K_L4.1 GB 6.8 GB
Fits Get file →
IQ4_XS4.2 GB 6.8 GB
Fits Get file →
Q4_04.4 GB 7.0 GB
Fits Get file →
Q4_04.4 GB 7.0 GB
Fits Get file →
Q4_04.4 GB 7.0 GB
Fits Get file →
Q4_04.4 GB 7.0 GB
Fits Get file →
Q4_K_S4.4 GB 7.1 GB
Fits Get file →
Q4_K_M4.6 GB 7.3 GB
Tight Get file →
Q5_K_S5.3 GB 7.9 GB
Tight Get file →
Q5_K_M5.4 GB 8.0 GB
Too big Get file →
Q6_K6.2 GB 8.8 GB
Too big Get file →

For 8‑GB VRAM use Q4_K_M (file size 4.65 GB, estimated 9.4 GB memory). For 16‑GB VRAM use Q5_K_M (5.4 GB, 10.2 GB memory). For 32‑GB VRAM use Q6_K (6.2 GB, 11 GB memory).

What GPU do you need for Holger 7B v0.1?

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 IQ3_XXS (3.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.2 GB file, about 11.0 GB in use).

Which Holger 7B v0.1 quant should you choose?

Q4_K_M is the usual starting point for Holger 7B v0.1: it balances file size and quality well. Here it is a 4.6 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 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
Parameters7.55B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyHolger
Licenseapache-2.0
Downloads (HF)550
Last updated2024-11-13

Frequently asked questions about Holger 7B v0.1

How much VRAM does Holger 7B v0.1 need?

About 9.4 GB at Q4_K_M with an 8K context window. That is the 4.6 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 Holger 7B v0.1 on an 8 GB GPU?

Yes, with IQ3_XXS: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Holger 7B v0.1 GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.7 GB, IQ2_M is 2.8 GB and 18 more.

What context length does Holger 7B v0.1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Holger 7B v0.1 GGUF?

The files are on Hugging Face in the mradermacher/Holger-7B-v0.1-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 Holger 7B v0.1 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.

Can I run Holger 7B v0.1 on 8 GB VRAM?

Use the Q4_K_M quant, which estimates 9.4 GB memory at 8‑k context. It may fit with 8‑GB VRAM if batching is minimal.

Does Holger 7B support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of Holger-7B-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Holger models

All Holger →

Other small models

All small models →