RA

RAG Gate 4B

RagGGUF by mradermacherUpdated 2026-10-07
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant1.9 GB
Quick answer

RAG Gate 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 12 quants, from 1.9 GB (Q2_K) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

RAG Gate 4B – a 4.21B parameter Qwen3.5‑based RAG decision model

RAG Gate 4B is a 4.21B parameter model fine‑tuned from Qwen3.5‑4B. It sits after retrieval and before generation, emitting one token: Answer, Retrieve, or Stop. The model is released under Apache‑2.0 and supports reasoning and tools.

Good at

  • Deciding when to retrieve
  • Generating short action tokens
  • Supporting multi‑hop reasoning

Limits

  • No vision support
  • Requires 8 k context for estimates
  • No explicit language list

Best for

  • RAG pipelines needing a decision head
  • Low‑latency retrieval control
  • Fine‑tuned Qwen3.5 deployments

Who it’s for. Developers building RAG systems that need a lightweight decision model. The model is ideal for applications that require a single token to trigger further retrieval or generation steps.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 3.5 GB
Fits Get file →
Q3_K_S2.1 GB 3.6 GB
Fits Get file →
Q3_K_M2.3 GB 3.8 GB
Fits Get file →
Q3_K_L2.4 GB 4.0 GB
Fits Get file →
IQ4_XS2.5 GB 4.1 GB
Fits Get file →
Q4_K_S2.6 GB 4.1 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_S3.0 GB 4.6 GB
Fits Get file →
Q5_K_M3.1 GB 4.6 GB
Fits Get file →
Q6_K3.5 GB 5.0 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
F168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.71 GB, memory 4.3 GB). If 12 GB VRAM is available, Q6_K (3.46 GB, 5 GB memory) offers higher precision. For the lowest memory footprint, Q2_K (1.92 GB, 3.5 GB memory) is suitable.

What GPU do you need for RAG Gate 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 Q3_K_L (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 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 F16 (8.4 GB file, about 10.0 GB in use).

Which RAG Gate 4B quant should you choose?

Q4_K_M is the usual starting point for RAG Gate 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 Q2_K at 1.9 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
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyRag
Licenseapache-2.0
Downloads (HF)796
Last updated2026-10-07

Frequently asked questions about RAG Gate 4B

How much VRAM does RAG Gate 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 RAG Gate 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 RAG Gate 4B GGUF?

It depends on the quant: Q2_K is 1.9 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, IQ4_XS is 2.5 GB, Q4_K_S is 2.6 GB and 6 more.

What context length does RAG Gate 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 RAG Gate 4B GGUF?

The files are on Hugging Face in the mradermacher/RAG-Gate-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 RAG Gate 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 RAG Gate 4B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 4.3 GB VRAM at 8 k context, which fits within 8 GB. The Q2_K quant uses 3.5 GB and is even lighter.

Does RAG Gate 4B support vision?

No, the model has no vision capabilities and is text‑only.

What license applies to RAG Gate 4B?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rag models

All Rag →

Other small models

All small models →