▸ DEVICE UNDER TEST
NVIDIA GeForce GTX 750 — 1 GB VRAM.
▸ GEFORCE GTX 750 SPEC
- BRAND
- NVIDIA
- VRAM
- 1 GB GDDR5
- BANDWIDTH
- 80.2 GB/s
- FP16 COMPUTE
- 1.1 TFLOPS
- FP32 COMPUTE
- 1.1 TFLOPS
- CUDA CORES
- 512
- TDP
- 55 W
- ARCHITECTURE
- Maxwell
▸ AI CAPABILITY
23/ 428 models @ Q4
With 1 GB VRAM and 80.2 GB/s bandwidth, this GPU handles models up to 0.6B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~9 tok/s.
§ 01TOP MODELS FOR GEFORCE GTX 750
23 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| Qwen3 0.6B | 0.6B | 0.9 GB | 107 | 19.1 |
| Qwen3-Embedding 0.6B | 0.6B | 0.9 GB | 107 | — |
| Falcon-H1R Tiny 0.6B | 0.6B | 0.9 GB | 107 | — |
| Falcon Perception 0.6B | 0.6B | 0.9 GB | 107 | — |
| BGE-M3 | 0.568B | 0.8 GB | 113 | 63.0 |
| Snowflake Arctic Embed L v2.0 | 0.568B | 0.8 GB | 113 | — |
| Falcon-H1 0.5B | 0.5B | 0.8 GB | 128 | 41.7 |
| Qwen 1.5 0.5B | 0.5B | 0.8 GB | 128 | 9.9 |
| Qwen 2.5 0.5B | 0.5B | 0.8 GB | 128 | 19.4 |
| SmolVLM 500M | 0.5B | 0.8 GB | 128 | — |
| SmolLM2 360M | 0.36B | 0.7 GB | 178 | 8.2 |
| LFM2 350M | 0.35B | 0.7 GB | 183 | 46.3 |
| GPT-2 Medium 345M | 0.345B | 0.7 GB | 186 | 5.9 |
| bge-large-en-v1.5 335M | 0.335B | 0.7 GB | 192 | 62.3 |
| mxbai-embed-large-v1 | 0.335B | 0.7 GB | 192 | 64.7 |
| Snowflake Arctic Embed L | 0.335B | 0.7 GB | 192 | 56.0 |
| Snowflake Arctic Embed M v2.0 | 0.305B | 0.7 GB | 210 | — |
| Gemma 3 270M | 0.27B | 0.7 GB | 238 | 12.6 |
| SmolVLM 256M | 0.256B | 0.6 GB | 251 | 28.3 |
| SmolLM2 135M | 0.135B | 0.6 GB | 475 | 7.0 |