AP

Apocrypha-7b

ApocryphaGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

Apocrypha-7b 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 21 quants, from 1.6 GB (IQ1_S) to 5.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Apocrypha‑7b: a 7.24 B llama model for pseudo‑philosophical counseling

Apocrypha‑7b is a 7.24 B llama architecture model trained on theory‑of‑mind, counseling, and occult datasets. It is designed to act as a sounding board for ideas and role‑play in a helper role. The model is released under apache‑2.0.

Good at

  • Role‑playing counseling scenarios
  • Philosophical discussion
  • Idea organization

Limits

  • No vision support
  • Large context required
  • No medical advice

Best for

  • Chatbot counseling prototypes
  • Philosophy discussion bots
  • Idea brainstorming tools

Who it’s for. Developers building conversational agents that need a reflective, pseudo‑counseling tone. The model is suitable for research and prototyping, not for clinical use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.8 GB 3.3 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 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 →
IQ4_XS3.9 GB 5.5 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_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 →

For 8 GB VRAM use IQ1_S or IQ1_M (file sizes 1.61 GB and 1.75 GB, memory ~3.2 GB and 3.3 GB). For 12 GB VRAM use IQ2_S or Q2_K (file sizes 2.31 GB and 2.72 GB, memory ~3.9 GB and 4.3 GB). For 24 GB VRAM use Q5_K_M or Q6_K (file sizes 5.13 GB and 5.94 GB, memory ~6.7 GB and 7.5 GB).

What GPU do you need for Apocrypha-7b?

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_S (2.3 GB file, about 3.9 GB in use).
  • 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).

Which Apocrypha-7b quant should you choose?

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

If memory is tight, the smallest file is IQ1_S at 1.6 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 bymradermacher
FamilyApocrypha
Licenseapache-2.0
Downloads (HF)2,520
Last updated2024-08-02

Frequently asked questions about Apocrypha-7b

How much VRAM does Apocrypha-7b 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 Apocrypha-7b 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 Apocrypha-7b GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 15 more.

What context length does Apocrypha-7b 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 Apocrypha-7b GGUF?

The files are on Hugging Face in the mradermacher/Apocrypha-7b-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 Apocrypha-7b 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 Apocrypha‑7b on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations; they require about 3.2–3.3 GB of VRAM at 8 k context.

Does Apocrypha‑7b support vision?

No, the model has no vision capabilities.

Is Apocrypha‑7b suitable for medical advice?

No, it is not medical advice and should not be used for clinical decisions.

Other GGUFs of Apocrypha-7b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Apocrypha models

All Apocrypha →

Other small models

All small models →