other
0.75B parameters
Commercial OK
Reviewed May 2026

Kanarya 750M

Smaller Kanarya variant — 750M parameters. Runs on CPU or 4GB GPU comfortably. Useful for low-resource Turkish text classification, embeddings, or completion tasks where latency matters more than quality.

License: Apache-2.0·Context: 2,048 tokens

Overview

Smaller Kanarya variant — 750M parameters. Runs on CPU or 4GB GPU comfortably. Useful for low-resource Turkish text classification, embeddings, or completion tasks where latency matters more than quality.

Strengths

  • Runs on CPU at usable speeds for short completions
  • Same Turkish-native tokenizer as Kanarya 2B
  • Fits in 2GB VRAM — phone-class hardware viable

Weaknesses

  • Quality cap is materially below 2B sibling; only pick this if you need the size
  • 2K context limit
  • Base completion model only — no chat template

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M0.4 GB1 GB

Get the model

HuggingFace

Original weights

huggingface.co/asafaya/kanarya-750m

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Kanarya 750M.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step up
More capable — bigger memory footprint
Step down
Smaller — faster, runs on weaker hardware
No verdicted models in the next tier down yet.

Frequently asked

What's the minimum VRAM to run Kanarya 750M?

1GB of VRAM is enough to run Kanarya 750M at the Q4_K_M quantization (file size 0.4 GB). Higher-quality quantizations need more.

Can I use Kanarya 750M commercially?

Yes — Kanarya 750M ships under the Apache-2.0, which permits commercial use. Always read the license text before deployment.

What's the context length of Kanarya 750M?

Kanarya 750M supports a context window of 2,048 tokens (about 2K).

Source: huggingface.co/asafaya/kanarya-750m

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify Kanarya 750M runs on your specific hardware before committing money.