HO

Hornybot Mara POV

HornybotGGUF by mradermacherUpdated 2026-09-15
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant3.8 GB
Quick answer

Hornybot Mara POV needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 3.8 GB (Q2_K) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Hornybot Mara POV – a fine‑tuned Qwen3.5 model for adult roleplay

Hornybot Mara POV is an 8.95B‑parameter Qwen3.5 fine‑tune focused on first‑person adult roleplay. It is designed for fictional interaction between adults and includes a compact system prompt embedded in the GGUF files. The model supports reasoning, roleplay, tools, and vision capabilities.

Good at

  • First‑person adult roleplay
  • Reasoning and tool use
  • Vision support

Limits

  • No vision projector or MTP speculative‑decoding weights
  • License review pending for derivative release
  • No third‑party content clearance

Best for

  • Adult roleplay scripts
  • Interactive fiction testing
  • Custom character dialogue

Who it’s for. Developers and content creators looking for a specialized adult roleplay model. The model is suitable for local deployment with llama.cpp or transformers, but requires careful review of output due to potential profanity and explicit content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 5.4 GB
Fits Get file →
Q3_K_S4.3 GB 5.8 GB
Fits Get file →
Q3_K_M4.6 GB 6.2 GB
Fits Get file →
Q3_K_L4.9 GB 6.5 GB
Fits Get file →
IQ4_XS5.2 GB 6.8 GB
Fits Get file →
Q4_K_S5.4 GB 6.9 GB
Fits Get file →
Q4_K_M5.6 GB 7.2 GB
Tight Get file →
Q5_K_S6.3 GB 7.9 GB
Tight Get file →
Q5_K_M6.5 GB 8.0 GB
Too big Get file →
Q6_K7.4 GB 8.9 GB
Too big Get file →
Q8_09.5 GB 11.1 GB
Too big Get file →
F1617.9 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, the Q6_K quant (file size 7.36 GB, estimated memory 8.9 GB) is a good choice. If memory is tighter, Q4_K_M (5.63 GB, 7.2 GB) or Q3_K_M (4.62 GB, 6.2 GB) provide lower memory usage. Larger quants like Q8_0 or F16 offer higher fidelity but need more VRAM.

What GPU do you need for Hornybot Mara POV?

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 Q3_K_S (4.3 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.9 GB file, about 19.5 GB in use).

Which Hornybot Mara POV quant should you choose?

Q4_K_M is the usual starting point for Hornybot Mara POV: it balances file size and quality well. Here it is a 5.6 GB file.

The Q8_0 file is 9.5 GB, about 1.7 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 3.8 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

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyHornybot
Downloads (HF)652
Last updated2026-09-15

Frequently asked questions about Hornybot Mara POV

How much VRAM does Hornybot Mara POV need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Hornybot Mara POV on an 8 GB GPU?

Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hornybot Mara POV GGUF?

It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, IQ4_XS is 5.2 GB, Q4_K_S is 5.4 GB and 6 more.

What context length does Hornybot Mara POV support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Hornybot Mara POV GGUF?

The files are on Hugging Face in the mradermacher/Hornybot-Mara-POV-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 Hornybot Mara POV on 8 GB VRAM?

Yes, the Q6_K quant requires about 8.9 GB of VRAM at 8 k context, which is close to 8 GB but may need a slightly lower context or batch size.

Does the model support vision?

The GGUF files contain no vision projector or MTP speculative‑decoding weights, so vision is not supported.

Is the model licensed for redistribution?

The derivative release is pending licensing review; the upstream Apache 2.0 license is retained but does not guarantee clearance of third‑party material.

Other GGUFs of Hornybot-Mara-POV

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Hornybot models

All Hornybot →

Other small models

All small models →