Ryzen AI Max+ PRO 495 (Gorgon Halo) systems
AMD Ryzen AI Max+ PRO 495 (Gorgon Halo) systems: 192 GB of memory at 273 GB/s. Below: the open models it can run, estimated at 192 GB with an 8K context. Strix Halo's successor: 192 GB of LPDDR5X at 273 GB/s, up to 160 GB of it assignable to the GPU, the most memory of any unified-memory PC here; 180B-class models such as Qwen3.8-Flash-Next fit.
Last updated: 2026-10-14
Specifications
What it can run
Best-quality quantization that fits with a 8K context, and the estimated generation speed. Estimates, not benchmarks. See the methodology.
| Model | Params | Best quant | Memory | tok/s (est.) |
|---|---|---|---|---|
| Qwen3.8-Flash-Next | 180B (6B) | Q5_K_M | 125.9 GiB | 38 |
| Qwen3.5-122B-A10B | 122B (10B) | Q8_0 | 127.4 GiB | 15 |
| Mistral Small 4 119B (2603) | 119B (6.5B) | Q8_0 | 124.3 GiB | 24 |
| gpt-oss-120b | 117B (5.1B) | Q8_0 | 122.3 GiB | 30 |
| Llama 4 Scout 17B-16E Instruct | 109B (17B) | Q8_0 | 115.3 GiB | 9.1 |
| GLM-4.5-Air | 106B (12B) | Q8_0 | 112.1 GiB | 13 |
| Qwen3-Coder-Next (80B-A3B) | 80B (3B) | Q8_0 | 83.8 GiB | 51 |
| Llama 3.3 70B Instruct | 70B | FP16 | 139.9 GiB | 1.2 |
| Qwen3.5-35B-A3B | 35B (3B) | FP16 | 69.1 GiB | 27 |
| Qwen3.6-35B-A3B | 35B (3B) | FP16 | 69.1 GiB | 27 |
| Qwen3-32B | 32.8B | FP16 | 66.6 GiB | 2.5 |
| DeepSeek-R1-Distill-Qwen-32B | 32.76B | FP16 | 66.6 GiB | 2.5 |
| Gemma 4 31B IT | 30.7B | FP16 | 61.6 GiB | 2.7 |
| Qwen3-30B-A3B (2507) | 30.5B (3.3B) | FP16 | 60.9 GiB | 25 |
| Qwen3-Coder-30B-A3B-Instruct | 30.5B (3.3B) | FP16 | 60.9 GiB | 25 |
| GLM-4.7-Flash (30B-A3B) | 30B (3B) | FP16 | 59.6 GiB | 27 |
| Qwen3.5-27B | 27B | FP16 | 53.8 GiB | 3.0 |
| Qwen3.6-27B | 27B | FP16 | 53.8 GiB | 3.0 |
| Qwen3.8-27B | 27B | FP16 | 53.8 GiB | 3.0 |
| Gemma 3 27B IT | 27B | FP16 | 54.3 GiB | 3.0 |
| Gemma 4 26B A4B IT | 25.2B (3.8B) | FP16 | 50.1 GiB | 22 |
| Mistral Small 3.2 24B Instruct (2506) | 24B | FP16 | 48.7 GiB | 3.4 |
| Magistral Small 1.2 (2509) | 24B | FP16 | 48.7 GiB | 3.4 |
| Devstral Small 2 24B Instruct (2512) | 24B | FP16 | 48.7 GiB | 3.4 |
| gpt-oss-20b | 21B (3.6B) | FP16 | 41.8 GiB | 23 |
| Phi-4 (14B) | 14B | FP16 | 29.4 GiB | 5.9 |
| Gemma 3 12B IT | 12B | FP16 | 24.8 GiB | 6.8 |
| Gemma 4 12B Unified IT | 11.95B | FP16 | 24.2 GiB | 6.9 |
| Qwen3.5-9B | 9B | FP16 | 18.4 GiB | 9.1 |
| Qwen3-8B | 8.2B | FP16 | 17.7 GiB | 10.0 |
| DeepSeek-R1-0528-Qwen3-8B | 8.19B | FP16 | 17.6 GiB | 10 |
| Llama 3.1 8B Instruct | 8B | FP16 | 17.1 GiB | 10 |
| Gemma 4 E4B IT | 8B | FP16 | 16.4 GiB | 10 |
| Llama 3.2 3B Instruct | 3.21B | FP16 | 7.7 GiB | 26 |
| Kimi K2.6 | 1000B (32B) | Doesn't fit | – | – |
| DeepSeek-R1-0528 (671B) | 671B (37B) | Doesn't fit | – | – |
| DeepSeek-V4-Flash | 284B (13B) | Doesn't fit | – | – |
Prices
No prices recorded for this device yet. All prices →
Frequently asked questions
Which LLMs can the Ryzen AI Max+ PRO 495 (Gorgon Halo) systems run?
With 192 GB and an 8K context, the largest models that fit include: Qwen3.8-Flash-Next, Qwen3.5-122B-A10B, Mistral Small 4 119B (2603), gpt-oss-120b, Llama 4 Scout 17B-16E Instruct. See the full table below.
How fast is the Ryzen AI Max+ PRO 495 (Gorgon Halo) systems for local LLMs?
Generation speed is mostly set by memory bandwidth (273 GB/s). For Llama 3.1 8B Instruct at FP16, expect roughly 10 tokens/s; bigger models are slower.
Can the Ryzen AI Max+ PRO 495 (Gorgon Halo) systems run 70B models?
Yes. Llama 3.3 70B Instruct fits on the Ryzen AI Max+ PRO 495 (Gorgon Halo) systems (192 GB) at FP16 with an 8K context, using about 139.9 GiB, at an estimated 1.2 tokens/s.