AMD Gorgon Halo 192GB vs Intel Arc Pro B70 for local LLMs
6 reports on the AMD Gorgon Halo 192GB and 17 on the Intel Arc Pro B70
Which is faster for local LLMs?
On Qwen3.8 27B at 8-bit, the AMD Gorgon Halo 192GB has 8.1 generation tokens/s (one run); prompt processing 466.0 tokens/s (one run); the Intel Arc Pro B70 has 16.7 generation tokens/s (one run); prompt processing 1047.0 tokens/s (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 2.2x higher on the Intel Arc Pro B70 (273 GB/s on the AMD Gorgon Halo 192GB, 608 on the Intel Arc Pro B70).
- Memory
- 192GB unified
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 61.4 TFLOPS
- Reports
- 6
- Memory
- 32GB
- Memory bandwidth
- 608 GB/s
- FP16 compute
- 183.5 TFLOPS
- Reports
- 17
Measured on both
Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | AMD Gorgon Halo 192GB | Intel Arc Pro B70 |
|---|---|---|
| Qwen3.8 27B8-bit | 8.1one runPP 466.0 (one run)llama.cppcontext not stated | 16.7one runPP 1047.0 (one run)llama.cppcontext not stated |
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.
| Model | AMD Gorgon Halo 192GB | Intel Arc Pro B70 |
|---|---|---|
| Qwen3.8 27B | 2.8 t/sFP16 | 15.2 t/sQ6_K |
| Qwen3.8 125B · 6B active | 9.5 t/sQ8_0 | 18.6 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 12.5 t/sQ4_K_M | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 10.0 t/sFP16 | 55.3 t/sQ5_K_M |
| Qwen3.6 27B | 2.8 t/sFP16 | 15.2 t/sQ6_K |
| Gemma 4 26B · 4B active | 7.5 t/sFP16 | 38.8 t/sQ6_K |
| GLM-5.3 320B · 18B active | 6.7 t/sQ3_K_M | doesn't fit at these settings |
Change the context, RAM or model in the calculator: AMD Gorgon Halo 192GB · Intel Arc Pro B70
Every report on each card, with its source: AMD Gorgon Halo 192GB · Intel Arc Pro B70