LL

ShiningValiant

LlamaGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant26.3 GB
Quick answer

ShiningValiant needs about 45.4 GB of memory at Q4_K_M (a 42.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 26.3 GB (Q2_K) to 48.3 GB (Q5_K_S).

ShiningValiant 70B chat model fine‑tuned on Llama 2

ShiningValiant is a 69‑billion‑parameter chat model built on Llama 2 architecture. It is fine‑tuned on private and public data for insight, creativity, and structured reasoning. The current version is 1.4 with expanded personality capability.

Good at

  • Chatting with friendly tone
  • Structured reasoning
  • Knowledgeable responses

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License is llama2

Best for

  • Personal assistant scripts
  • Creative writing prompts
  • Knowledge‑heavy Q&A

Who it’s for. Developers and researchers who need a large chat model with a friendly personality. It is suitable for local deployment using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.3 GB 28.1 GB
Too big Get file →
IQ3_XS29.1 GB 31.0 GB
Too big Get file →
IQ3_S30.8 GB 32.6 GB
Too big Get file →
Q3_K_S30.8 GB 32.6 GB
Too big Get file →
IQ3_M31.8 GB 33.6 GB
Too big Get file →
Q3_K_M34.1 GB 36.0 GB
Too big Get file →
Q3_K_L37.0 GB 38.8 GB
Too big Get file →
IQ4_XS38.0 GB 39.9 GB
Too big Get file →
Q4_K_S40.1 GB 41.9 GB
Too big Get file →
Q4_K_M42.3 GB 44.1 GB
Too big Get file →
Q5_K_S48.3 GB 50.1 GB
Too big Get file →

For 8 GB VRAM use Q2_K (26.3 GB file, ~29.5 GB memory). For 12 GB VRAM use Q3_K_S (30.75 GB file, ~33.9 GB memory). For 16 GB VRAM use Q4_K_M (42.26 GB file, ~45.4 GB memory). Estimates are approximate.

What GPU do you need for ShiningValiant?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (26.3 GB file, about 29.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.3 GB file, about 45.4 GB in use).

Which ShiningValiant quant should you choose?

Q4_K_M is the usual starting point for ShiningValiant: it balances file size and quality well. Here it is a 42.3 GB file.

If memory is tight, the smallest file is Q2_K at 26.3 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama2
Downloads (HF)920
Last updated2024-12-16

Frequently asked questions about ShiningValiant

How much VRAM does ShiningValiant need?

About 45.4 GB at Q4_K_M with an 8K context window. That is the 42.3 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 ShiningValiant on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ShiningValiant GGUF?

It depends on the quant: Q2_K is 26.3 GB, IQ3_XS is 29.1 GB, IQ3_S is 30.8 GB, Q3_K_S is 30.8 GB, IQ3_M is 31.8 GB, Q3_K_M is 34.1 GB and 5 more.

What context length does ShiningValiant support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download ShiningValiant GGUF?

The files are on Hugging Face in the mradermacher/ShiningValiant-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 ShiningValiant 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 ShiningValiant on 8 GB VRAM?

Use the Q2_K quant; it requires about 29.5 GB memory at 8k context, so 8 GB VRAM is insufficient for inference.

Does ShiningValiant support vision tasks?

No, the model has no vision capability.

What license applies to ShiningValiant?

The model is licensed under llama2.

Other GGUFs of Llama2-70B-ShiningValiant

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →