UN

Unholy-Thoth-8B-v2

UnholyGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters8.03B
Context1024K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Unholy-Thoth-8B-v2 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Unholy-Thoth-8B-v2 – 8.03B llama model in GGUF format

Unholy-Thoth-8B-v2 is a 8.03B parameter llama model quantized into GGUF files. It offers a range of quantization options from IQ1_S to Q6_K, allowing users to balance file size and memory usage. The model supports a context length of 1048576 tokens.

Good at

  • Large context handling
  • Flexible quantization choices
  • Compact file sizes

Limits

  • No license specified
  • No vision support
  • Large memory requirement for higher quants

Best for

  • Chat applications with long context
  • Fine‑tuning on limited GPU memory
  • Research on quantization effects

Who it’s for. Developers and researchers who need a llama model with extensive context and multiple quantization options. Suitable for those running on GPUs with 8 GB or more VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.02 GB file, 3.6 GB memory) or IQ1_M (2.16 GB file, 3.7 GB memory). If 12 GB VRAM is available, Q4_K_M (4.92 GB file, 6.5 GB memory) or Q5_K_M (5.73 GB file, 7.3 GB memory) are viable. Higher quants require more than 12 GB VRAM.

What GPU do you need for Unholy-Thoth-8B-v2?

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Unholy-Thoth-8B-v2 quant should you choose?

Q4_K_M is the usual starting point for Unholy-Thoth-8B-v2: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 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
Parameters8.03B
Layers32
Trained context1,048,576 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyUnholy
Downloads (HF)532
Last updated2024-08-02

Frequently asked questions about Unholy-Thoth-8B-v2

How much VRAM does Unholy-Thoth-8B-v2 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Unholy-Thoth-8B-v2 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Unholy-Thoth-8B-v2 GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 15 more.

What context length does Unholy-Thoth-8B-v2 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). 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 Unholy-Thoth-8B-v2 GGUF?

The files are on Hugging Face in the mradermacher/Unholy-Thoth-8B-v2-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Unholy-Thoth-8B-v2 on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations, which estimate 3.6–3.7 GB memory at 8k context.

What is the largest quant that fits in 12 GB VRAM?

Q4_K_M or Q5_K_M, each estimating 6.5–7.3 GB memory at 8k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Unholy models

All Unholy →

Other small models

All small models →