JU

fblgit_juanako-7b-una

JuanakoGGUF by TheBlokeUpdated 2023-12-01
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

fblgit_juanako-7b-una needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.1 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Juanako 7B UNA – a 7.24B parameter Llama model fine‑tuned on ultrafeedback data

fblgit_juanako-7b-una is a 7.24B parameter Llama model fine‑tuned on the HuggingFaceH4/ultrafeedback_binarized dataset. It uses Uniform Neural Alignment (UNA) for alignment between transformer layers. The model is released under the Apache‑2.0 license.

Good at

  • High‑quality text generation
  • Reasoning tasks
  • Instruction following

Limits

  • No vision support
  • Requires 8‑k context for full performance
  • Large VRAM needed for higher quants

Best for

  • Chatbots on local GPUs
  • Fine‑tuning for domain‑specific prompts
  • Educational content generation

Who it’s for. Developers and researchers who need a powerful Llama‑based model for local deployment. The model is suitable for those who can allocate sufficient GPU memory and want a model that performs well on reasoning benchmarks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.37 GB file, ~5.9 GB memory). For 12 GB VRAM, Q5_K_M (5.13 GB file, ~6.7 GB memory). For 24 GB VRAM, Q6_K (5.94 GB file, ~7.5 GB memory). Estimates are approximate.

What GPU do you need for fblgit_juanako-7b-una?

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 Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which fblgit_juanako-7b-una quant should you choose?

Q4_K_M is the usual starting point for fblgit_juanako-7b-una: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 Q2_K at 3.1 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTheBloke
FamilyJuanako
Licenseapache-2.0
Downloads (HF)453
Last updated2023-12-01

Frequently asked questions about fblgit_juanako-7b-una

How much VRAM does fblgit_juanako-7b-una need?

About 5.9 GB at Q4_K_M 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 fblgit_juanako-7b-una on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of fblgit_juanako-7b-una GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 6 more.

What context length does fblgit_juanako-7b-una 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 fblgit_juanako-7b-una GGUF?

The files are on Hugging Face in the TheBloke/juanako-7B-UNA-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 fblgit_juanako-7b-una 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 this model on 8 GB VRAM?

Yes, with the Q4_K_M quant, which requires about 5.9 GB VRAM at 8‑k context.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of juanako-7b-UNA

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Juanako models

All Juanako →

Other small models

All small models →