UN

fblgit_una-cybertron-7b-v3-oma

UnaGGUF by TheBlokeUpdated 2023-12-15
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

fblgit_una-cybertron-7b-v3-oma 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.

fblgit_una-cybertron-7b-v3-oma – a 7.24B llama model in GGUF format

fblgit_una-cybertron-7b-v3-oma is a 7.24B parameter llama model quantised for local deployment. It supports 32768 token context and is released under apache-2.0. The model is available in multiple quantisations for different memory budgets.

Good at

  • Mathematics and logic
  • Deep reasoning over prompts
  • High context retention

Limits

  • No vision support
  • Requires GPU for best performance
  • License is apache-2.0

Best for

  • Chat applications
  • Code generation
  • Research prototyping

Who it’s for. Developers and researchers who need a large llama model that can run locally with a range of quantisations. The model is suitable for users with GPU memory from 4.7 GB to 9.3 GB and who prefer an open‑source license.

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 (est. 5.9 GB) or Q5_K_M (est. 6.7 GB). For 12 GB VRAM Q6_K (est. 7.5 GB) is suitable. Larger models such as Q8_0 (est. 9.3 GB) require 12 GB or more. Memory estimates are approximate.

What GPU do you need for fblgit_una-cybertron-7b-v3-oma?

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_una-cybertron-7b-v3-oma quant should you choose?

Q4_K_M is the usual starting point for fblgit_una-cybertron-7b-v3-oma: 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
FamilyUna
Licenseapache-2.0
Downloads (HF)1,068
Last updated2023-12-15

Frequently asked questions about fblgit_una-cybertron-7b-v3-oma

How much VRAM does fblgit_una-cybertron-7b-v3-oma 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_una-cybertron-7b-v3-oma 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_una-cybertron-7b-v3-oma 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_una-cybertron-7b-v3-oma 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_una-cybertron-7b-v3-oma GGUF?

The files are on Hugging Face in the TheBloke/una-cybertron-7B-v3-OMA-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_una-cybertron-7b-v3-oma 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, use Q4_K_M or Q5_K_M which estimate 5.9 GB or 6.7 GB of VRAM at 8K context.

Does this model support vision tasks?

No, the model has no vision capability.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of una-cybertron-7b-v3-OMA

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Una models

All Una →

Other small models

All small models →