▸ DEVICE UNDER TEST
NVIDIA GeForce GTX 560 Ti 448 — 1 GB VRAM.
▸ GEFORCE GTX 560 TI 448 SPEC
- BRAND
- NVIDIA
- VRAM
- 1 GB GDDR5
- BANDWIDTH
- 152 GB/s
- FP16 COMPUTE
- 1.3 TFLOPS
- FP32 COMPUTE
- 1.3 TFLOPS
- CUDA CORES
- 448
- TDP
- 210 W
- ARCHITECTURE
- Fermi 2.0
▸ AI CAPABILITY
27/ 449 models @ Q4
With 1 GB VRAM and 152 GB/s bandwidth, this GPU handles models up to 0.94B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~17 tok/s.
§ 01TOP MODELS FOR GEFORCE GTX 560 TI 448
27 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| InternVL3 1B | 0.94B | 1.1 GB | 129 | 58.0 |
| Qwen 3.5 0.8B | 0.87B | 1.0 GB | 140 | 22.5 |
| GPT-2 Large 774M | 0.81B | 1.0 GB | 150 | 5.6 |
| Qwen3 0.6B | 0.75B | 0.9 GB | 162 | 19.1 |
| LFM2 700M | 0.74B | 0.9 GB | 164 | 50.4 |
| Qwen 1.5 0.5B | 0.62B | 0.9 GB | 196 | 9.9 |
| Qwen3-Embedding 0.6B | 0.6B | 0.9 GB | 203 | — |
| Falcon-H1R Tiny 0.6B | 0.6B | 0.9 GB | 203 | — |
| Falcon Perception 0.6B | 0.6B | 0.9 GB | 203 | — |
| BGE-M3 | 0.568B | 0.8 GB | 214 | 63.0 |
| Snowflake Arctic Embed L v2.0 | 0.568B | 0.8 GB | 214 | — |
| Falcon-H1 0.5B | 0.52B | 0.8 GB | 234 | 41.7 |
| Qwen 2.5 0.5B | 0.5B | 0.8 GB | 243 | 19.4 |
| SmolVLM 500M | 0.5B | 0.8 GB | 243 | — |
| GPT-2 Medium 345M | 0.38B | 0.7 GB | 320 | 5.9 |
| SmolLM2 360M | 0.36B | 0.7 GB | 338 | 8.2 |
| LFM2 350M | 0.35B | 0.7 GB | 347 | 46.3 |
| bge-large-en-v1.5 335M | 0.335B | 0.7 GB | 363 | 62.3 |
| mxbai-embed-large-v1 | 0.335B | 0.7 GB | 363 | 64.7 |
| Snowflake Arctic Embed L | 0.335B | 0.7 GB | 363 | 56.0 |