Products · Intel · Workstation card
Intel Arc Pro B50
- GPU
- Intel Arc Pro B50
- VRAM
- 16 GB
- Launch price
- $349
- Released
- 2025
Specifications
| Maker | Intel |
|---|---|
| Type | Workstation card |
| GPU | Intel Arc Pro B50 |
| Video memory (VRAM) | 16.0 GB |
| Usable for AI models | 16.0 GB |
| Memory bandwidth | 224 GB/s |
| FP16 compute | 13.9 TFLOPS |
| Notes | Intel-built low-profile dual-slot, 70 W, bus-powered |
| Product page | www.intel.com (opens in a new tab) |
Cards built on the same GPU with the same memory run AI models at practically the same speed; factory overclocks and coolers change results by only a few percent.
Best LLMs for the Intel Arc Pro B50
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q3_K_M | 14.4 GB | 58.0 tok/s | Runs welltight fit |
| 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q3_K_M | 15.6 GB | 52.4 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 20B | MXFP4 | 13.5 GB | 51.6 tok/s | Runs great |
| 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Mellum2.1 Thinking (12B-A2.5B) | Q6_K | 11.5 GB | 48.2 tok/s | Runs great |
| 67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q5_K_M | 15.9 GB | 82.7 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 12B | Q4_K_M | 9.4 GB | 17.6 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B Thinking | Q4_K_M | 15.2 GB | 56.7 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | DiffusionGemma 26B-A4B IT | Q3_K_M | 14.5 GB | 55.6 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q2_K | 15.9 GB | 84.6 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q2_K | 15.7 GB | 84.6 tok/s | Runs welltight fit |
Best Image models for the Intel Arc Pro B50
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q8 GGUF | 10.5 GB | 7.9 s | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP8 | 12.6 GB | 15 s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP8 | 12.4 GB | 35 s | Runs well |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP8 | 14.5 GB | 20 s | Runs welltight fit |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP8 | 11.7 GB | 12 s | Runs greatencoder in RAM |
| 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | FP8 | 12.6 GB | 1.7 min | Slow |
Best Video models for the Intel Arc Pro B50
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 10.8 GB | 2.6 min | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 11.0 GB | 6.2 min | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP8 | 12.8 GB | 24.7 min | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B | FP8 | 14.3 GB | 18.5 min | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B I2V | FP8 | 14.9 GB | 18.5 min | Slowtight fit |
Best Decision models for the Intel Arc Pro B50
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 2.8 GB | 56 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 2.8 GB | 56 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | F16 | 2.4 GB | 38 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | F16 | 1.7 GB | 25 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | F16 | 2.8 GB | 56 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q8_0 | 3.1 GB | 122 ms | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | d1 3B | Q6_K | 4.0 GB | 130 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | F16 | 1.2 GB | 27 ms | Runs great |
Spec sources
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.