IN

Inf Retriever v1 Pro

InfGGUF by mradermacherUpdated 2026-10-08
Download on Hugging Face
Parameters7.07B
Context128K
Layers28
Architectureqwen2
Smallest quant2.8 GB
Quick answer

Inf Retriever v1 Pro needs about 5.3 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.8 GB (Q2_K) to 14.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Inf Retriever v1 Pro – a retrieval‑focused Qwen2 model

Inf Retriever v1 Pro is a 7.07 billion‑parameter Qwen2 model trained for dense retrieval. It converts complex queries into concise, search‑optimized forms for RAG systems. The model is released under Apache‑2.0 and supports 131072‑token context.

Good at

  • Efficient query rewriting
  • Dense retrieval prep
  • RAG integration

Limits

  • No vision support
  • Requires 131072‑token context
  • No mixture of experts

Best for

  • Retrieval‑augmented generation
  • Search‑optimized query generation
  • Complex query distillation

Who it’s for. Developers building RAG pipelines or search engines that need a lightweight, high‑performance retriever. The model is suitable for applications requiring concise query transformation from verbose inputs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 3.8 GB
Fits Get file →
Q3_K_S3.3 GB 4.2 GB
Fits Get file →
Q3_K_M3.6 GB 4.5 GB
Fits Get file →
Q3_K_L3.9 GB 4.8 GB
Fits Get file →
IQ4_XS4.0 GB 4.9 GB
Fits Get file →
Q4_K_S4.1 GB 5.1 GB
Fits Get file →
Q4_K_M4.4 GB 5.3 GB
Fits Get file →
Q5_K_S4.9 GB 5.9 GB
Fits Get file →
Q5_K_M5.1 GB 6.0 GB
Fits Get file →
Q6_K5.8 GB 6.8 GB
Fits Get file →
Q8_07.5 GB 8.5 GB
Too big Get file →
F1614.1 GB 15.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (4.15 GB file, 5.1 GB memory) or Q3_K_M (3.57 GB file, 4.5 GB memory). If 12 GB VRAM is available, Q5_K_S (4.94 GB file, 5.9 GB memory) offers higher precision. Larger VRAM allows Q8_0 (7.52 GB file, 8.5 GB memory) or F16 (14.14 GB file, 15.1 GB memory).

What GPU do you need for Inf Retriever v1 Pro?

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 Q2_K (2.8 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (5.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.8 GB file, about 6.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.5 GB file, about 8.5 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (14.1 GB file, about 15.1 GB in use).

Which Inf Retriever v1 Pro quant should you choose?

Q4_K_M is the usual starting point for Inf Retriever v1 Pro: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.5 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 2.8 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

Architectureqwen2
Parameters7.07B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized bymradermacher
FamilyInf
Licenseapache-2.0
Downloads (HF)774
Last updated2026-10-08

Frequently asked questions about Inf Retriever v1 Pro

How much VRAM does Inf Retriever v1 Pro need?

About 5.3 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Inf Retriever v1 Pro on an 8 GB GPU?

Yes, with Q6_K: the 5.8 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Inf Retriever v1 Pro GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 3.3 GB, Q3_K_M is 3.6 GB, Q3_K_L is 3.9 GB, IQ4_XS is 4.0 GB, Q4_K_S is 4.1 GB and 6 more.

What context length does Inf Retriever v1 Pro support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Inf Retriever v1 Pro GGUF?

The files are on Hugging Face in the mradermacher/inf-retriever-v1-pro-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 Inf Retriever v1 Pro 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 Inf Retriever v1 Pro on 8 GB VRAM?

Yes, using the Q4_K_S quant (4.15 GB file, 5.1 GB memory) fits within 8 GB VRAM.

What is the context length of this model?

The model supports 131072 tokens of context.

Is the model licensed for commercial use?

It is released under the Apache‑2.0 license, which permits commercial use.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Inf models

All Inf →

Other small models

All small models →