RH

rheia

RheiaGGUF by mradermacherUpdated 2024-08-09
Download on Hugging Face
Parameters2.51B
Context8K
Layers18
Architecturegemma
Smallest quant1.2 GB
Quick answer

rheia needs about 2.3 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 1.2 GB (Q2_K) to 5.0 GB (F16).

Rheia, a 2.51B‑parameter Gemma model in GGUF format

Rheia is a 2.51B‑parameter Gemma architecture model available in multiple GGUF quantizations. It supports a 8192‑token context window. No license or language metadata is provided.

Good at

  • Fast inference on low‑memory GPUs
  • Supports 8192‑token context
  • Multiple quant options for trade‑offs

Limits

  • No license information
  • No language or vision capabilities listed
  • No Mixture of Experts

Best for

  • Local chatbot deployments
  • Fine‑tuning on small datasets
  • Low‑cost inference on edge devices

Who it’s for. Developers and researchers needing a lightweight Gemma‑based model for local inference. The model is suitable for those who can manage the lack of explicit license and language support details.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 1.8 GB
Fits Get file →
IQ3_XS1.2 GB 1.9 GB
Fits Get file →
Q3_K_S1.3 GB 1.9 GB
Fits Get file →
IQ3_S1.3 GB 1.9 GB
Fits Get file →
IQ3_M1.3 GB 2.0 GB
Fits Get file →
Q3_K_M1.4 GB 2.0 GB
Fits Get file →
Q3_K_L1.5 GB 2.1 GB
Fits Get file →
IQ4_XS1.5 GB 2.2 GB
Fits Get file →
Q4_K_S1.6 GB 2.2 GB
Fits Get file →
Q4_K_M1.6 GB 2.3 GB
Fits Get file →
Q5_K_S1.8 GB 2.4 GB
Fits Get file →
Q5_K_M1.8 GB 2.5 GB
Fits Get file →
Q6_K2.1 GB 2.7 GB
Fits Get file →
Q8_02.7 GB 3.3 GB
Fits Get file →
F165.0 GB 5.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.63 GB file, ~2.3 GB VRAM) or Q5_K_M (1.84 GB file, ~2.5 GB VRAM). For 4 GB VRAM, Q3_K_M (1.38 GB file, ~2 GB VRAM) or Q3_K_S (1.29 GB file, ~1.9 GB VRAM) are suitable. Higher precision quants require more memory.

What GPU do you need for rheia?

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 Q8_0 (2.7 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (5.0 GB file, about 5.7 GB in use).

Which rheia quant should you choose?

Q4_K_M is the usual starting point for rheia: it balances file size and quality well. Here it is a 1.6 GB file.

The Q8_0 file is 2.7 GB, about 1.6 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 1.2 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

Architecturegemma
Parameters2.51B
Layers18
Trained context8,192 tokens
KV cache (fp16)18 KB per token

Source

Quantized bymradermacher
FamilyRheia
Downloads (HF)612
Last updated2024-08-09

Frequently asked questions about rheia

How much VRAM does rheia need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.6 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 rheia on an 8 GB GPU?

Yes, with F16: the 5.0 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rheia GGUF?

It depends on the quant: Q2_K is 1.2 GB, IQ3_XS is 1.2 GB, Q3_K_S is 1.3 GB, IQ3_S is 1.3 GB, IQ3_M is 1.3 GB, Q3_K_M is 1.4 GB and 9 more.

What context length does rheia support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download rheia GGUF?

The files are on Hugging Face in the mradermacher/rheia-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Rheia on 8 GB VRAM?

Yes, Q4_K_M or Q5_K_M quants fit within 8 GB VRAM, using approximately 2.3–2.5 GB of memory at 8k context.

Does Rheia support vision tasks?

No, the model does not provide vision capabilities.

What is the maximum context length for Rheia?

The model supports up to 8192 tokens of context.

Other GGUFs of rheia

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rheia models

All Rheia →

Other tiny models

All tiny models →