RI

RIFA PRO 3B

RifaGGUF by mradermacherUpdated 2026-09-07
Download on Hugging Face
Parameters3.08B
Context64K
Layers36
Architecturesmollm3
Smallest quant0.0 GB
Quick answer

RIFA PRO 3B needs about 3.0 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

RIFA PRO 3B – 3.08B parameter bilingual chat model

RIFA PRO 3B is a 3.08B parameter model in the Rifa family, built on the smollm3 architecture. It supports reasoning and tool usage, trained on 65536 context tokens. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning tasks
  • Tool integration
  • Bilingual English‑Bangla chat

Limits

  • No vision support
  • May hallucinate – verify facts
  • Requires system prompt for consistent branding

Best for

  • Chatbots needing bilingual support
  • Tool‑enabled assistants
  • Rapid prototyping with low VRAM

Who it’s for. Developers building lightweight chat applications or assistants that require reasoning and tool use in English and Bangla. The model is suitable for users with moderate GPU memory who want a balance between performance and resource usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.1 GB
Fits Get file →
IQ1_S0.8 GB 1.9 GB
Fits Get file →
IQ1_M0.8 GB 1.9 GB
Fits Get file →
IQ2_XXS0.9 GB 2.0 GB
Fits Get file →
IQ2_XS1.0 GB 2.1 GB
Fits Get file →
IQ2_S1.0 GB 2.2 GB
Fits Get file →
IQ2_M1.1 GB 2.2 GB
Fits Get file →
Q2_K_S1.2 GB 2.3 GB
Fits Get file →
Q2_K1.3 GB 2.4 GB
Fits Get file →
IQ3_XXS1.3 GB 2.4 GB
Fits Get file →
IQ3_XS1.4 GB 2.5 GB
Fits Get file →
Q3_K_S1.4 GB 2.5 GB
Fits Get file →
IQ3_S1.4 GB 2.5 GB
Fits Get file →
IQ3_M1.5 GB 2.6 GB
Fits Get file →
Q3_K_M1.6 GB 2.7 GB
Fits Get file →
Q3_K_L1.7 GB 2.8 GB
Fits Get file →
IQ4_XS1.7 GB 2.8 GB
Fits Get file →
IQ4_NL1.8 GB 2.9 GB
Fits Get file →
Q4_01.8 GB 2.9 GB
Fits Get file →
Q4_K_S1.8 GB 2.9 GB
Fits Get file →
Q4_K_M1.9 GB 3.0 GB
Fits Get file →
Q4_12.0 GB 3.1 GB
Fits Get file →
Q5_K_S2.2 GB 3.3 GB
Fits Get file →
Q5_K_M2.2 GB 3.3 GB
Fits Get file →
Q6_K2.5 GB 3.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.92 GB file, ~3 GB memory at 8k context). For 6 GB VRAM, Q3_K_M (1.57 GB file, ~2.7 GB memory). If memory is very tight, Q2_XXS (0.93 GB file, ~2 GB memory) is an option. File sizes and memory estimates are approximate.

What GPU do you need for RIFA PRO 3B?

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 Q6_K (2.5 GB file, about 3.6 GB in use).

Which RIFA PRO 3B quant should you choose?

Q4_K_M is the usual starting point for RIFA PRO 3B: it balances file size and quality well. Here it is a 1.9 GB file.

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

Architecturesmollm3
Parameters3.08B
Layers36
Trained context65,536 tokens
KV cache (fp16)72 KB per token

Source

Quantized bymradermacher
FamilyRifa
Licenseapache-2.0
Downloads (HF)664
Last updated2026-09-07

Frequently asked questions about RIFA PRO 3B

How much VRAM does RIFA PRO 3B need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 1.9 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 RIFA PRO 3B on an 8 GB GPU?

Yes, with Q6_K: the 2.5 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of RIFA PRO 3B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.8 GB, IQ1_M is 0.8 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.0 GB and 19 more.

What context length does RIFA PRO 3B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.

Where can I download RIFA PRO 3B GGUF?

The files are on Hugging Face in the mradermacher/RIFA-PRO-3B-i1-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 RIFA PRO 3B 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 RIFA PRO 3B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 3 GB of VRAM at 8k context, fitting within an 8 GB GPU.

Does RIFA PRO 3B support vision?

No, the model has no vision capability.

Other GGUFs of RIFA-PRO-3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rifa models

All Rifa →

Other tiny models

All tiny models →