AU

Denis Pplx Autojev 27b

AutojevGGUF by thomasgauthierUpdated 2026-09-25
Download on Hugging Face
Parameters25.6B
Context256K
Layers64
Architectureqwen35
Smallest quant15.8 GB
Quick answer

Denis Pplx Autojev 27b needs about 18.5 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Denis Pplx Autojev 27b – a multimodal decision model

Denis Pplx Autojev 27b is a 25.6 billion‑parameter multimodal model based on Qwen3.8‑27B. It returns probabilities over supplied choices in a single forward pass per question. The model supports vision inputs via a projector and is served through a custom AutoJev‑enabled llama.cpp fork.

Good at

  • Multimodal decision making
  • Single‑pass choice probability output
  • Vision support via projector

Limits

  • Requires AutoJev‑enabled llama.cpp fork
  • Large VRAM needed for full weights (~49 GiB BF16)
  • Only one quant available (Q4_K_M)

Best for

  • Decision‑making agents
  • Rapid choice‑based inference
  • Vision‑enabled question answering

Who it’s for. Developers building autonomous agents that need quick, probability‑based decisions with optional image input. The model is suited for research and production environments that can run the custom llama.cpp fork and provide sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M15.8 GB 18.5 GB
Too big Get file →

The Q4_K_M quant is 15.83 GB and estimates 18.5 GB of VRAM at 8 k context. It is the only quant available, so use it if your GPU can accommodate the memory estimate. For larger contexts, memory usage will increase proportionally.

What GPU do you need for Denis Pplx Autojev 27b?

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: the best quant that fits is Q4_K_M (15.8 GB file, about 18.5 GB in use).

Which Denis Pplx Autojev 27b quant should you choose?

Q4_K_M is the usual starting point for Denis Pplx Autojev 27b: it balances file size and quality well. Here it is a 15.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters25.6B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bythomasgauthier
FamilyAutojev
Licenseapache-2.0
Downloads (HF)636
Last updated2026-09-25

Frequently asked questions about Denis Pplx Autojev 27b

How much VRAM does Denis Pplx Autojev 27b need?

About 18.5 GB at Q4_K_M with an 8K context window. That is the 15.8 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 Denis Pplx Autojev 27b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Denis Pplx Autojev 27b GGUF?

It depends on the quant: Q4_K_M is 15.8 GB.

What context length does Denis Pplx Autojev 27b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Denis Pplx Autojev 27b GGUF?

The files are on Hugging Face in the thomasgauthier/autojev-27b-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 Denis Pplx Autojev 27b 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?

No. The Q4_K_M quant requires approximately 18.5 GB of VRAM at 8 k context, which exceeds 8 GB.

Does the model support text only?

Yes. Text requests do not need the vision projector, but the model still requires the AutoJev‑enabled llama.cpp fork.

What license applies to the GGUF weights?

The GGUF weights are licensed under Apache‑2.0, the same as the original model.

Similar models

Browse all →

More from thomasgauthier

All by thomasgauthier →

Other medium models

All medium models →