gemma
9.2B parameters
Commercial OK
Reviewed May 2026

YTU Turkish Gemma 9B v0.1

YTU Turkish Gemma 9B v0.1 is a Gemma 2 based Turkish instruction model from the YTU CE COSMOS ecosystem. The benchmarked Ollama tag is an alibayram GGUF distribution of that public model.

License: Gemma·Context: 8,192 tokens

Overview

YTU Turkish Gemma 9B v0.1 is a Gemma 2 based Turkish instruction model from the YTU CE COSMOS ecosystem. The benchmarked Ollama tag is an alibayram GGUF distribution of that public model.

Strengths

  • Modern Gemma 2 base with Turkish SFT/DPO signals
  • Commercial use allowed under the Gemma terms
  • Fits comfortably on 16GB consumer GPUs at Q4_K_M

Weaknesses

  • 8K context limit is shorter than Mistral 7B v0.2 derivatives
  • Gemma chat-template behavior needs runtime-specific care
  • The benchmarked Ollama build is a third-party GGUF distribution

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_M5.8 GB8 GB

Get the model

Ollama

One-line install

ollama run alibayram/turkish-gemma-9b-v0.1:latestRead our Ollama review →

HuggingFace

Original weights

huggingface.co/ytu-ce-cosmos/Turkish-Gemma-9b-v0.1

Source repository — direct quantization required.

Benchmarks

Real measurements on real hardware. Numbers ship with the runner version, quant, and date.

2 runs on record
HardwareProvenanceQuantCtxTokens / secVRAMTTFTDate
NVIDIA GeForce RTX 5080
EditorialM
Q4_K_M2K
101.1tok/s
——May 28, 26
NVIDIA GeForce RTX 3080 16GB (Mobile)
EditorialM
Q4_K_M4K
66.0tok/s
—369 msJun 2, 26

What to do next

Got this model running on real hardware? Share what you measured — the form arrives with the model pre-selected.

Submit a benchmark for YTU Turkish Gemma 9B v0.1
OrBrowse the benchmark roadmapCompare hardware options

Hardware that runs this

Cards with enough VRAM for at least one quantization of YTU Turkish Gemma 9B v0.1.

NVIDIA GB200 NVL72
13824GB · nvidia
AMD Instinct MI355X
288GB · amd
AMD Instinct MI325X
256GB · amd
AMD Instinct MI300X
192GB · amd
NVIDIA B200
192GB · nvidia
NVIDIA H100 NVL
188GB · nvidia
NVIDIA H200
141GB · nvidia
NVIDIA H200 NVL (PCIe)
141GB · nvidia
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.

Frequently asked

What's the minimum VRAM to run YTU Turkish Gemma 9B v0.1?

8GB of VRAM is enough to run YTU Turkish Gemma 9B v0.1 at the Q4_K_M quantization (file size 5.8 GB). Higher-quality quantizations need more.

Can I use YTU Turkish Gemma 9B v0.1 commercially?

Yes — YTU Turkish Gemma 9B v0.1 ships under the Gemma, which permits commercial use. Always read the license text before deployment.

What's the context length of YTU Turkish Gemma 9B v0.1?

YTU Turkish Gemma 9B v0.1 supports a context window of 8,192 tokens (about 8K).

How do I install YTU Turkish Gemma 9B v0.1 with Ollama?

Run `ollama pull alibayram/turkish-gemma-9b-v0.1:latest` to download, then `ollama run alibayram/turkish-gemma-9b-v0.1:latest` to start a chat session. The default quantization is Q4_K_M.

Source: huggingface.co/ytu-ce-cosmos/Turkish-Gemma-9b-v0.1

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

Related — keep moving

Compare hardware
Buyer guides
When it doesn't work
Recommended hardware
Before you buy

Verify YTU Turkish Gemma 9B v0.1 runs on your specific hardware before committing money.

Will it run on my hardware? →Custom hardware comparison →GPU recommender (4 questions) →