NO

NORA

NoraGGUF by mradermacherUpdated 2026-10-14
Download on Hugging Face
Parameters3.1B
Context125K
Layers36
Architectureqwen2vl
Smallest quant1.3 GB
Quick answer

NORA needs about 2.7 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 24 quants, from 1.3 GB (Q2_K) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

NORA – 3.1B Qwen2VL model with vision support

NORA is a 3.1B parameter Qwen2VL model that supports vision tasks. It is available in multiple GGUF quantizations ranging from Q2_K to F16. The model was quantized by mradermacher and is based on hungchiayu/NORA.

Good at

  • Vision‑enabled text generation
  • Image‑to‑text tasks
  • Multimodal prompt handling

Limits

  • No explicit license information
  • No language metadata provided
  • Requires 8k context for memory estimates

Best for

  • Local inference on GPUs with 8–16 GB VRAM
  • Rapid prototyping of vision‑enabled LLMs
  • Educational demos of multimodal models

Who it’s for. Developers and researchers who need a lightweight vision‑capable LLM for local deployment. The model is suitable for experimentation and educational purposes where detailed licensing is not critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.3 GB 2.1 GB
Fits Get file →
Q2_K1.3 GB 2.1 GB
Fits Get file →
Q3_K_S1.5 GB 2.3 GB
Fits Get file →
Q3_K_S1.5 GB 2.3 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
IQ4_XS1.8 GB 2.6 GB
Fits Get file →
IQ4_XS1.8 GB 2.6 GB
Fits Get file →
Q4_K_S1.8 GB 2.6 GB
Fits Get file →
Q4_K_S1.8 GB 2.6 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.93 GB file, ~2.7 GB RAM). For 12 GB VRAM, Q5_K_M (2.23 GB file, ~3 GB RAM) offers a good balance. If higher precision is needed and 16 GB VRAM is available, F16 (6.19 GB file, ~7 GB RAM) can be used.

What GPU do you need for NORA?

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 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).

Which NORA quant should you choose?

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

The Q8_0 file is 3.3 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 1.3 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

Architectureqwen2vl
Parameters3.1B
Layers36
Trained context128,000 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
FamilyNora
Base modelhungchiayu/NORA
Downloads (HF)991
Last updated2026-10-14

Frequently asked questions about NORA

How much VRAM does NORA need?

About 2.7 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 NORA on an 8 GB GPU?

Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NORA GGUF?

It depends on the quant: Q2_K is 1.3 GB, Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_M is 1.6 GB and 18 more.

What context length does NORA support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download NORA GGUF?

The files are on Hugging Face in the mradermacher/NORA-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 NORA on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S quantizations which require about 2.6–2.7 GB of VRAM at 8k context.

Does NORA support text‑only tasks?

Yes, but it is primarily designed for vision‑enabled tasks; text‑only usage is supported.

What is the context length of NORA?

NORA was trained with a context of 128000 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nora models

All Nora →

Other tiny models

All tiny models →