Fits comfortably

Running Mistral Turkish v2 (brooqs) on NVIDIA GeForce RTX 5080

NVIDIA GeForce RTX 5080 runs Mistral Turkish v2 (brooqs) comfortably at Q4_0 with 10 GB of headroom for context.

By Eruo Fredoline·Latest benchmark evidence May 28, 2026

Model size

7.2B params
Mistral Turkish v2 (brooqs) →

Memory available

16 GB
NVIDIA GeForce RTX 5080 →

Recommended quant

Q4_0
Highest quality that fits

Quick start with Ollama

1. Install
ollama pull brooqs/mistral-turkish-v2:latest
2. Run
ollama run brooqs/mistral-turkish-v2:latest

Default quant in Ollama is Q4_K_M. To use a different quant, append it: brooqs/mistral-turkish-v2:latest-q5_K_M.

Variants and what fits

QuantizationFile sizeVRAM requiredFits on NVIDIA GeForce RTX 5080?
Q4_04.1 GB6 GB
Yes

Real benchmarks

ToolQuantContexttok/sVRAM usedDateEvidenceExport
—Q4_02,048161.1 tok/s—May 28, 2026Measured here
operator: fred-oline
DetailSourceJSON

Frequently asked

Can NVIDIA GeForce RTX 5080 run Mistral Turkish v2 (brooqs)?

NVIDIA GeForce RTX 5080 runs Mistral Turkish v2 (brooqs) comfortably at Q4_0 with 10 GB of headroom for context.

What quantization should I use?

Q4_0 is the highest-quality variant of Mistral Turkish v2 (brooqs) that fits in 16 GB VRAM. Lower-bit quants will be smaller but lose some quality.

How fast will it be?

Measured at 161.1 tok/s on this combination in our testing.

See also: Mistral Turkish v2 (brooqs), NVIDIA GeForce RTX 5080, all benchmarks.

Reviewed by RunLocalAI Editorial. See our editorial policy.