RAG Gate 9B 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.
RAG Gate 9B – a Qwen3.5‑based decision model for retrieval‑augmented generation
RAG Gate 9B is a LoRA fine‑tune of Qwen/Qwen3.5‑9B that decides whether to answer, retrieve more, or stop in a RAG pipeline. It outputs a single token after the prefill "Final action:". Accuracy on a held‑out test set rises from .686 to .955.
Good at
- Decision making in RAG pipelines
- Low unsupported‑answer rate
- Fast inference with small quants
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license restricts commercial redistribution
Best for
- RAG pipelines needing a decision token
- Low‑latency inference on edge GPUs
- Fine‑tuning other Qwen3.5 models
Who it’s for. Developers building retrieval‑augmented generation systems who need a lightweight decision model. It is suitable for applications that require a single token to control the next step of the pipeline.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_S | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| F16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (5.35 GB, 6.9 GB memory) or Q3_K_M (4.62 GB, 6.2 GB memory). For 12 GB VRAM, Q5_K_S (6.31 GB, 7.9 GB memory) or Q4_K_M (5.63 GB, 7.2 GB memory) are good choices. Larger models like Q8_0 (9.53 GB, 11.1 GB memory) require 16 GB or more.
What GPU do you need for RAG Gate 9B?
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 RAG Gate 9B quant should you choose?
Q4_K_M is the usual starting point for RAG Gate 9B: 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
Source
Frequently asked questions about RAG Gate 9B
How much VRAM does RAG Gate 9B 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 RAG Gate 9B 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 RAG Gate 9B 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 RAG Gate 9B 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 9B GGUF?
The files are on Hugging Face in the mradermacher/RAG-Gate-9B-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 9B 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 9B on 8 GB VRAM?
Yes, the Q4_K_S quant uses 5.35 GB file size and requires about 6.9 GB VRAM at 8k context.
Does RAG Gate 9B support image inputs?
No, the model has no vision capabilities and only processes text.
What license applies to RAG Gate 9B?
The model is released under the Apache‑2.0 license.