Framework Desktop (Ryzen AI Max+ PRO 495)
Ryzen AI Max+ PRO 495 · Agent Computer · Announced, not yet shipping
The Framework Desktop (Ryzen AI Max+ PRO 495) is Framework's desktop built on the Ryzen AI Max+ PRO 495, and it gives a local model about 144GB of usable AI memory at 256 GB/s. No verified price is currently on record, so the price block below shows its status rather than a number. It scores 46.1 overall on the AIPC Score.
Price and memory shown are for the 192GB / 2TB configuration.
AIPC Score: 46.1
- AI memory69.5
- AI compute11.8
- Memory bandwidth14.2
- Model compatibility79.3
- GPU capability11.8
- NPU capability50
- Software support70
- Power efficiency100
- Expandability60
- Price/value26.5
Specifications
- AI Memory
- 144GB
- CPU
- Ryzen AI Max+ PRO 495 (16 Zen 5 cores)
- GPU
- Radeon 8060S (40 CU)
- NPU
- XDNA 2 (50 TOPS)
- Memory bandwidth
- 256 GB/s
- Storage
- 2TB
- Configuration
- 192GB / 2TB
- Type
- Desktop
How we calculate AI memory: About 75% of system memory, the Windows Variable Graphics Memory default. Linux allows more. Source →
Configurations
| Configuration | AI Memory | Memory bandwidth | Price | Retailer |
|---|---|---|---|---|
| 192GB / 2TB | 144GB | 256 GB/s | Price awaiting re-verification | Framework |
What can this PC run?
| Model | Quantization | Fits | Mode | State | Speed |
|---|---|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-7B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Qwen-7B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Qwen-14B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Qwen-14B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Qwen-32B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Qwen-32B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Llama-70B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| DeepSeek-R1-Distill-Llama-70B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 4B IT | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 4B IT | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 12B IT | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 12B IT | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 27B IT | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Gemma 3 27B IT | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.2 3B Instruct | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.2 3B Instruct | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.1 8B Instruct | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.1 8B Instruct | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.1 70B Instruct | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.1 70B Instruct | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.3 70B Instruct | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 3.3 70B Instruct | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 4 Scout 17B-16E Instruct | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Llama 4 Scout 17B-16E Instruct | Q8 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Mistral Small 3 (Mistral-Small-24B-Instruct-2501) | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Mistral Small 3 (Mistral-Small-24B-Instruct-2501) | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Devstral Small 1.1 (Devstral-Small-2507) | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Devstral Small 1.1 (Devstral-Small-2507) | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Mistral Medium 3.5 128B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Mistral Medium 3.5 128B | Q8 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Phi-4 | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Phi-4 | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-4B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-4B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-8B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-8B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-14B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-14B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-30B-A3B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-30B-A3B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-32B | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-32B | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Qwen3-235B-A22B | Q4 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| gpt-oss-20b | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| gpt-oss-20b | Q8 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| gpt-oss-120b | Q4 | Yes | Full memory | Calculated | Performance not yet benchmarked |
| gpt-oss-120b | Q8 | Limited | Offload required | Calculated | Performance not yet benchmarked |
| Whisper large-v3 | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| FLUX.1 schnell | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| FLUX.1 dev | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Stable Diffusion XL Base 1.0 | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Stable Diffusion 3.5 Large | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| HunyuanVideo | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Wan2.1 T2V 14B | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
| Wan2.2 T2V A14B | Published | Yes | Full memory | Calculated | Performance not yet benchmarked |
Does not fit (11)
- DeepSeek-R1 Q4: needs 469.8GB
- DeepSeek-R1 Q8: needs 821.9GB
- DeepSeek-V3 Q4: needs 469.8GB
- DeepSeek-V3 Q8: needs 821.9GB
- GLM-5.2 Q4: needs 527GB
- GLM-5.2 Q8: needs 922.1GB
- Kimi-K2-Instruct Q4: needs 699.2GB
- Kimi-K2-Instruct Q8: needs 1223.9GB
- Llama 4 Maverick 17B-128E Instruct Q4: needs 280.9GB
- Llama 4 Maverick 17B-128E Instruct Q8: needs 490.7GB
- Qwen3-235B-A22B Q8: needs 289.1GB
Alternatives
- Dell Pro Max T2 (RTX PRO 5000)
48GB · AI Score 47
No verified price
- Apple Mac Studio (M5 Ultra)
72GB · AI Score 43.9
$5,499
- Corsair Vengeance i7500 (RTX 5090)
32GB · AI Score 50.4
No verified price