← All machines

AMD unified memory · Framework

Framework Desktop (Ryzen AI Max 385)

The entry Framework Desktop with the 8-core, 32-CU Strix Halo part and 32GB. It handles small and mid-size models; the 32GB ceiling rules out the large ones.

Memory for models

24 GBassumption

AMD documents 96 GB only for 128 GB machines; this applies AMD's "Custom (75%)" Variable Graphics Memory setting to 32 GB.

Memory bandwidth

256 GB/s

Maker price

~$1,269

Largest at 4-bit

Qwen3.6 35B-A3B

22.4 GB at 8,192 tokens of context (an assumed limit, see Memory for models)

gpt-oss-20b, 4-bit

~61–77 tok/sestimate

no measurement on this hardware yet

Memory configurations

One page covers every memory option the maker sells. Prices are the maker’s list price for the cheapest configuration with that much memory.

MemoryPriceMemory the GPU can use
32 GB~$1,269
24 GB gpu-usable memoryassumption

AMD documents 96 GB only for 128 GB machines; this applies AMD's "Custom (75%)" Variable Graphics Memory setting to 32 GB. How GPU memory limits work on unified-memory machines.

What it runs at 4-bit

Every model in the catalog at its 4-bit file with 8,192 tokens of context. 19 of 41 fit. Speeds are the median of measured runs on the same chip where any exist; otherwise an estimate from memory bandwidth. Try other quants and context lengths.

ModelNeedsFitGeneration speed
Kimi K32.8T, 104B active · UD-Q4_K_XL1406.8 GBcontext memory estimatedDoes not fit
DeepSeek V4 Pro1.6T, 49B active · Q4_K_M890.5 GBcontext memory not countedDoes not fit
Kimi K2.61T, 32B active · UD-Q4_K_XL545.7 GBcontext memory estimatedDoes not fit
DeepSeek V4.1 Flash552B, 16B active · Q4 (DwarfStar)484.5 GBDoes not fit
GLM-5.3753.3B · UD-Q4_K_XL437.4 GBcontext memory estimatedDoes not fit
DeepSeek V3.2671B, 37B active · Q4_K_M379.6 GBcontext memory estimatedDoes not fit
MiniMax M3428B, 23B active · Q4_K_M244.8 GBcontext memory not countedDoes not fit
Qwen3.5 397B-A17B397B, 17B active · Q4_K_M229.1 GBcontext memory estimatedDoes not fit
GLM-5.3 Flash320B, 18B active · UD-Q4_K_XL187.6 GBcontext memory estimatedDoes not fit
Hy3295B, 21B active · Q4_K_M173.6 GBDoes not fit
MiniMax M2.7228.7B · Q4_K_M132.7 GBDoes not fit
Qwen3.8 Flash-Next125B, 6B active · Q4_K_M113.1 GBcontext memory estimatedDoes not fit
Nemotron 3 Super 120B-A12B120B, 12B active · Q4_K_M82.6 GBcontext memory estimatedDoes not fit
Qwen3.5 122B-A10B122B, 10B active · Q4_K_M73.0 GBcontext memory estimatedDoes not fit
Mistral Medium 3.5 128B128B · Q4_K_M74.0 GBDoes not fit
GLM-4.5-Air106B, 12B active · Q4_K_M70.9 GBDoes not fit
Mistral Small 4 119B (2603)119B, 6.5B active · Q4_K_M69.3 GBcontext memory estimatedDoes not fit
Llama 4 Scout 17B-16E Instruct109B, 17B active · Q4_K_M62.4 GBcontext memory not countedDoes not fit
gpt-oss-120b117B, 5.1B active · MXFP4 (native)60.2 GBcontext memory estimatedDoes not fit
Qwen3 Coder Next80B, 3B active · Q4_K_M46.9 GBcontext memory estimatedDoes not fit
Llama 3.3 70B Instruct70B · Q4_K_M43.6 GBDoes not fit
Nemotron 3.5 Lightning 30B-A3B30B, 3B active · Q4_K_M25.3 GBcontext memory estimatedDoes not fit
Qwen3.6 35B-A3B35B, 3B active · Q4_K_M22.4 GBcontext memory estimatedFitsassumed limit~63–81 tok/sestimate
Ornith 1.5 35B-A3B35B, 3B active · Q4_K_M21.9 GBcontext memory estimatedFitsassumed limit~65–83 tok/sestimate
Qwen3 Coder 30B-A3B Instruct30.5B, 3.3B active · Q4_K_M19.5 GBFitsassumed limit~60–77 tok/sestimate
Gemma 4 31B IT30.7B · Q4_K_M18.9 GBcontext memory estimatedFitsassumed limit~9.5–11 tok/sestimate
Granite 4.2 30B29.3B · Q4_K_M20.3 GBFitsassumed limit~9.6–12 tok/sestimate
Qwen3.8 27B27B · Q4_K_M18.2 GBcontext memory estimatedFitsassumed limit~10.0–12 tok/sestimate
Gemma 4 26B-A4B IT25.2B, 3.8B active · Q4_K_M17.4 GBcontext memory estimatedFitsassumed limit~47–60 tok/sestimate
Qwen3.6 27B27B · Q4_K_M17.7 GBcontext memory estimatedFitsassumed limit~10–12 tok/sestimate
Devstral Small 2 24B (2512)24B · Q4_K_M16.1 GBFitsassumed limit~12–15 tok/sestimate
gpt-oss-20b21B, 3.6B active · MXFP4 (native)12.5 GBcontext memory estimatedFitsassumed limit~61–77 tok/sestimate
Phi-414.7B · Q4_K_M11.3 GBFitsassumed limit~20–23 tok/sestimate
Ministral 3 14B Reasoning (2512)13.9B · Q4_K_M10.4 GBFitsassumed limit~21–25 tok/sestimate
Gemma 4 12B IT11.95B · Q4_K_M8.2 GBcontext memory estimatedFitsassumed limit~24–29 tok/sestimate
Qwen3.5 9B9B · Q4_K_M7.0 GBcontext memory estimatedFitsassumed limit~31–37 tok/sestimate
Granite 4.2 8B8.8B · Q4_K_M7.9 GBFitsassumed limit~31–38 tok/sestimate
Gemma 4 E4B IT8B · Q4_K_M6.5 GBcontext memory not countedFitsassumed limit~57–68 tok/sestimate
Qwen3 8B8.2B · Q4_K_M7.3 GBFitsassumed limit~35–41 tok/sestimate
Llama 3.1 8B Instruct8B · Q4_K_M7.1 GBFitsassumed limit~35–42 tok/sestimate
Qwen3.5 4B4B · Q4_K_M4.3 GBcontext memory estimatedFitsassumed limit~63–76 tok/sestimate

Measured speeds

Nobody has published a run on this chip with a stated model, quant and backend that we could find. The speeds above are estimates.

Specifications

Chip
Ryzen AI Max 385
Memory
LPDDR5X-8000, 256-bit, soldered
Memory bandwidth
256 GB/s
FP16 compute
AMD quotes up to 126 overall TOPS (CPU+GPU+NPU, precision not stated) and no FP16 TFLOPS figure
NPU
50 TOPS
Software
ROCm, Vulkan, DirectML
Ships with
None (DIY Edition; Windows or Linux installed by the buyer)
Power
400 W (Internal 400W power supply (Framework spec))
Form factor
Mini PC
Networking
5GbE (Realtek RTL8126); two USB4 ports; optional 10GbE expansion card
Maker page
frame.work

Sources

  • frame.work: price $1,269 for Max 385 - 32GB
  • frame.work: 400W PSU, LPDDR5x-8000, 5GbE, release year 2025
  • amd.com: Radeon 8050S 32 CU, NPU 50 TOPS, LPDDR5x-8000 256-bit
  • rocm.docs.amd.com: Linux GTT default ~50% of RAM; raise via ttm pages_limit / amd-ttm --set (AMD example: 100GB on a 128GB system); keep BIOS VRAM small

Similar machines