Products · Framework · Mini PC
Framework Desktop
- Chips
- AMD Ryzen AI Max 385 or AMD Ryzen AI Max+ 395 or AMD Ryzen AI Max+ PRO 495
- Unified memory
- 32, 64, 128 or 192 GB
- Launch price
- $1,099–$1,999
- Released
- 2025
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| AMD Ryzen AI Max 385 | 32.0 GB | 24.0 GB | 256 GB/s | 461 of 622 | $1,099 |
| AMD Ryzen AI Max+ 395 | 64.0 GB | 48.0 GB | 256 GB/s | 481 of 622 | $1,599 |
| AMD Ryzen AI Max+ 395 | 128 GB | 96.0 GB | 256 GB/s | 510 of 622 | $1,999 |
| AMD Ryzen AI Max+ PRO 495 | 192 GB | 159 GB | 273 GB/s | 532 of 622 | — |
Specifications 32.0 GB configuration
| Maker | Framework |
|---|---|
| Type | Mini PC |
| Chip | AMD Ryzen AI Max 385 (32 GB) |
| Unified memory | 32.0 GB |
| Usable for AI models | 24.0 GB |
| Memory bandwidth | 256 GB/s |
| FP16 compute | 45.9 TFLOPS |
| Notes | 4.5 L mini-ITX; soldered LPDDR5X. Prices are launch (with case). Max+ PRO 495 / 192 GB config opened for pre-order 30 Sep 2026, price not yet published. |
| Product page | frame.work (opens in a new tab) |
Best LLMs for the Framework Desktop 32.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q4_K_M | 18.7 GB | 57.4 tok/s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q4_K_M | 23.8 GB | 69.2 tok/s | Runs welltight fit |
| 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q4_K_M | 20.1 GB | 51.9 tok/s | Runs great |
| 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 Flash (30B-A3B) | Q4_K_M | 22.0 GB | 69.2 tok/s | Runs welltight fit |
| 82Great quality (A) · 82 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen AgentWorld 35B-A3B | Q4_K_M | 23.8 GB | 69.2 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q3_K_M | 20.3 GB | 84.6 tok/s | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy-Memory 30B-A3B | Q4_K_M | 21.7 GB | 69.2 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q3_K_M | 19.9 GB | 84.6 tok/s | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q3_K_M | 20.3 GB | 84.6 tok/s | Runs great |
| 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q3_K_M | 19.9 GB | 84.6 tok/s | Runs great |
Best Image models for the Framework Desktop 32.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP8 | 20.2 GB | 9.0 s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | Q8 GGUF | 15.0 GB | 8.6 s | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP8 | 19.9 GB | 3.8 s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP8 | 12.4 GB | 12 s | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP16 | 18.1 GB | 2.3 s | Runs great |
| 83Great quality (A) · 83 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. | Z-Image Turbo | Q8 GGUF | 13.0 GB | 6.7 s | Runs great |
Best Video models for the Framework Desktop 32.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP8 | 19.7 GB | 4.1 min | Runs wellCPU offload |
| 83Great quality (A) · 83 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. | Bernini-R A14B (video generation + editing) | FP8 | 20.3 GB | 26.4 min | Slowencoder unloaded after use |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP16 | 17.5 GB | 58 s | Runs great |
| 45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP16 | 17.5 GB | 2.3 min | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | FramePack I2V (HunyuanVideo 13B) | FP8 | 19.6 GB | 14.7 min | Slowencoder unloaded after use |
Best Decision models for the Framework Desktop 32.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 7.1 GB | 106 ms | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q6_K | 6.1 GB | 98 ms | Runs great |
| 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 | 4.0 GB | 24 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q8_0 | 6.8 GB | 101 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | Q8_0 | 7.4 GB | 78 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 | 4.0 GB | 24 ms | Runs great |
| 82Great quality (A) · 82 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. | d1 3B | F16 | 8.8 GB | 81 ms | Runs great |
| 82Great quality (A) · 82 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. | mxbai-rerank-large v2 | F16 | 5.7 GB | 56 ms | Runs great |
Other products with the AMD Ryzen AI Max 385 (32 GB)
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.