128GB DDR5-6000 Kit (4x32GB)
$299
128GB DDR5-6000 memory kit for custom LLM builds. Enables CPU-based inference fallback and GPU layer offloading for models that exceed VRAM.
Specifications
Memory 128GB DDR5
Memory Bandwidth 96 GB/s
GPU Cores N/A
CPU Cores N/A
TDP 10W
Max Model (Q4) 0B parameters
Max Model (Q8) 0B parameters
Performance Tier High
Category PC Component
Performance Benchmarks
Pros
- 128GB enables CPU-based inference on large models
- DDR5-6000 high-speed memory
- Supports offloading layers from GPU
Cons
- CPU inference is much slower than GPU
- Requires 4 DIMM slots
Compatible Models (Q4)
Models that fit in 128GB at Q4 quantization
Llama 3.3 70B Instruct 70B
37GB required Llama 3.2 8B Instruct 8B
6GB required Llama 3.2 3B Instruct 3B
3.5GB required Mistral Large 2411 123B
63.5GB required Mistral 7B Instruct v0.3 7B
5.5GB required Gemma 3 27B Instruct 27B
15.5GB required Gemma 3 12B Instruct 12B
8GB required Qwen2.5 72B Instruct 72B
38GB required DeepSeek Coder V2 Instruct 236B
12.5GB required Qwen2.5 Coder 32B Instruct 32B
18GB required Qwen2.5 Coder 7B Instruct 7B
5.5GB required CodeLlama 34B Instruct 34B
19GB required StarCoder2 15B 15B
9.5GB required DeepSeek Coder 6.7B Instruct 6.7B
5.35GB required DeepSeek R1 671B
20.5GB required DeepSeek R1 Distill Qwen 32B 32B
18GB required DeepSeek R1 Distill Qwen 7B 7B
5.5GB required QwQ 32B 32B
18GB required Phi-4 14B
9GB required FLUX.1 Schnell 12B
6GB required + 11 more models
Compatible at Q8
31 models can run at Q8 quantization