Fits comfortably
Running Trendyol LLM Asure 12B on NVIDIA GeForce RTX 5080
NVIDIA GeForce RTX 5080 runs Trendyol LLM Asure 12B comfortably at GGUF_UNKNOWN with 6 GB of headroom for context.
Model size
11.8B params
Trendyol LLM Asure 12B →Memory available
Recommended quant
GGUF_UNKNOWN
Highest quality that fits
Quick start with Ollama
1. Install
ollama pull alibayram/Trendyol-LLM-Asure-12B:latest2. Run
ollama run alibayram/Trendyol-LLM-Asure-12B:latestDefault quant in Ollama is Q4_K_M. To use a different quant, append it: alibayram/Trendyol-LLM-Asure-12B:latest-q5_K_M.
Variants and what fits
| Quantization | File size | VRAM required | Fits on NVIDIA GeForce RTX 5080? |
|---|---|---|---|
| GGUF_UNKNOWN | 7.3 GB | 10 GB | Yes |
Real benchmarks
| Tool | Quant | Context | tok/s | VRAM used | Date | Evidence | Export |
|---|---|---|---|---|---|---|---|
| — | unknown | 2,048 | 79.1 tok/s | — | May 28, 2026 | Measured here operator: fred-oline | |
| — | Q4_K_M | 4,096 | 82.0 tok/s | — | May 28, 2026 | Measured here operator: fred-oline | |
| — | Q4_K_M | 8,192 | 61.5 tok/s | — | May 27, 2026 | Measured here operator: fred-oline |
Frequently asked
Can NVIDIA GeForce RTX 5080 run Trendyol LLM Asure 12B?
NVIDIA GeForce RTX 5080 runs Trendyol LLM Asure 12B comfortably at GGUF_UNKNOWN with 6 GB of headroom for context.
What quantization should I use?
GGUF_UNKNOWN is the highest-quality variant of Trendyol LLM Asure 12B that fits in 16 GB VRAM. Lower-bit quants will be smaller but lose some quality.
How fast will it be?
Measured at 79.1 tok/s on this combination in our testing.
See also: Trendyol LLM Asure 12B, NVIDIA GeForce RTX 5080, all benchmarks.
Reviewed by RunLocalAI Editorial. See our editorial policy.