RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Kumru 2B / on / NVIDIA GeForce RTX 5080
Fits comfortably

Running Kumru 2B on NVIDIA GeForce RTX 5080

NVIDIA GeForce RTX 5080 runs Kumru 2B comfortably at Q4_K_M with 14 GB of headroom for context.

By Fredoline Eruo·Latest benchmark evidence May 28, 2026

Model size

2.4B params
Kumru 2B →

Memory available

16 GB
NVIDIA GeForce RTX 5080 →

Recommended quant

Q4_K_M
Highest quality that fits

Quick start with Ollama

1. Install
ollama pull alibayram/kumru:latest
2. Run
ollama run alibayram/kumru:latest

Default quant in Ollama is Q4_K_M. To use a different quant, append it: alibayram/kumru:latest-q5_K_M.

Variants and what fits

QuantizationFile sizeVRAM requiredFits on NVIDIA GeForce RTX 5080?
Q4_K_M1.5 GB2 GB
Yes

Real benchmarks

ToolQuantContexttok/sVRAM usedDateEvidenceExport
—Q4_K_M2,048443.7 tok/s—May 28, 2026Measured here
operator: fred-oline
DetailSourceJSON

Frequently asked

Can NVIDIA GeForce RTX 5080 run Kumru 2B?

NVIDIA GeForce RTX 5080 runs Kumru 2B comfortably at Q4_K_M with 14 GB of headroom for context.

What quantization should I use?

Q4_K_M is the highest-quality variant of Kumru 2B that fits in 16 GB VRAM. Lower-bit quants will be smaller but lose some quality.

How fast will it be?

Measured at 443.7 tok/s on this combination in our testing.

See also: Kumru 2B, NVIDIA GeForce RTX 5080, all benchmarks.

Reviewed by RunLocalAI Editorial. See our editorial policy.