AP

APUS Reflex 4B

ApusGGUF by apus-ailabUpdated 2026-10-13
Download on Hugging Face
Parameters4.2B
Context256K
Layers32
Architectureqwen35
Smallest quant0.0 GB
Quick answer

APUS Reflex 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 0.0 GB to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

APUS Reflex 4B – a Qwen3.5‑based decision model for browser actions

APUS Reflex 4B is a 4.2 B parameter decision model built on Qwen3.5. It selects among 2–16 candidates for each request and returns a label distribution. The model is not a chat model and requires no thinking block when used with Ollama or llama.cpp.

Good at

  • Decision making for browser actions
  • Workflow routing
  • Natural‑language principle judgments

Limits

  • No chat capability
  • Requires --think=false for Ollama
  • Large VRAM needed for higher quantizations

Best for

  • Automated browser workflows
  • Decision‑oriented applications
  • Structured workflow generation

Who it’s for. Developers building decision engines or automated browser agents. The model is suitable for applications that need to evaluate multiple candidate actions and choose the best one.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
BF168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.71 GB file, ~4.3 GB memory at 8k context). For 12 GB VRAM, Q8_0 (4.48 GB file, ~6.1 GB memory) is recommended. BF16 requires ~10 GB memory and a 8.42 GB file.

What GPU do you need for APUS Reflex 4B?

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 the main file (0.0 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.7 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).

Which APUS Reflex 4B quant should you choose?

Q4_K_M is the usual starting point for APUS Reflex 4B: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.5 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.2B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byapus-ailab
FamilyApus
Licenseapache-2.0
Downloads (HF)8,981
Last updated2026-10-13

Frequently asked questions about APUS Reflex 4B

How much VRAM does APUS Reflex 4B need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 APUS Reflex 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of APUS Reflex 4B GGUF?

It depends on the quant: file is 0.0 GB, Q4_K_M is 2.7 GB, Q8_0 is 4.5 GB, BF16 is 8.4 GB.

What context length does APUS Reflex 4B 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 APUS Reflex 4B GGUF?

The files are on Hugging Face in the apus-ailab/APUS-Reflex-4B-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 APUS Reflex 4B 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 APUS Reflex 4B on 8 GB VRAM?

Yes, using the Q4_K_M quantization which uses about 4.3 GB of VRAM at 8k context.

Does this model support chat?

No, it is a decision model and does not provide chat functionality.

What is the context length?

The model was trained on 262,144 tokens and supports that context length.

Other GGUFs of APUS-Reflex-4B

Similar models

Browse all →

More from apus-ailab

All by apus-ailab →

More Apus models

All Apus →

Other small models

All small models →