RT

rtila assistant lite 1.5

RtilaGGUF by rtila-corporationUpdated 2026-03-13
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant5.6 GB
Quick answer

rtila assistant lite 1.5 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. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

RTILA Assistant Lite 1.5 – a unified 8.95B Qwen3.5 model

RTILA Assistant Lite 1.5 is a unified replacement for the previous RTILA family. Built on Qwen3.5-9B, it offers flagship‑level quality with a native 262,144 token context. The model is available in a single Q4_K_M quantized GGUF file.

Good at

  • High‑throughput inference with low latency
  • Large native context support
  • Unified multimodal foundation

Limits

  • No vision support in this quant
  • Requires 8.2 GB VRAM for Q4_K_M
  • No license information provided

Best for

  • Chatbots needing long context
  • Multilingual text generation
  • Efficient inference on mid‑range GPUs

Who it’s for. Developers and researchers who need a single, efficient model that replaces multiple variants. The model is suitable for applications requiring large context and multilingual support without the overhead of multiple versions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.6 GB 7.2 GB
Tight Get file →

The only available quant is Q4_K_M, file size 5.63 GB. It requires approximately 7.2 GB VRAM at 8 k context. This is suitable for GPUs with 8 GB or more VRAM. For larger memory budgets, the same quant can be used without change.

What GPU do you need for rtila assistant lite 1.5?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.6 GB file, about 7.2 GB in use).

Which rtila assistant lite 1.5 quant should you choose?

Q4_K_M is the usual starting point for rtila assistant lite 1.5: it balances file size and quality well. Here it is a 5.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byrtila-corporation
FamilyRtila
Downloads (HF)599
Last updated2026-03-13

Frequently asked questions about rtila assistant lite 1.5

How much VRAM does rtila assistant lite 1.5 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 rtila assistant lite 1.5 on an 8 GB GPU?

Yes, with Q4_K_M: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of rtila assistant lite 1.5 GGUF?

It depends on the quant: Q4_K_M is 5.6 GB.

What context length does rtila assistant lite 1.5 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 rtila assistant lite 1.5 GGUF?

The files are on Hugging Face in the rtila-corporation/rtila-assistant-lite-1.5 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run RTILA Assistant Lite 1.5 on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 7.2 GB VRAM at 8 k context, fitting within an 8 GB GPU.

What if I only have 4 GB VRAM?

The current quant requires more than 4 GB VRAM; a smaller quant is not available in the provided list.

Does the model support vision tasks?

No, the provided quant does not include vision capabilities.

Similar models

Browse all →

More from rtila-corporation

All by rtila-corporation →

More Rtila models

All Rtila →

Other small models

All small models →