Hardware for Running GPT-OSS 120B Locally
OpenAI's large open-weight MoE — its 117B total parameters fit a single high-memory box, and because only a fraction are active per token it runs far quicker than its total suggests.
Quick answer
GPT-OSS 120B (117B params) needs about 71 GB of memory at Q4 and 281 GB at full FP16 precision — both estimates including runtime overhead. It fits 9 boxes in our catalog, starting at the Apple Mac Studio M4 Max ($2,499+ — discontinued).
Estimated Memory Requirements
Estimated from the 117B parameter count (quantization × bytes/param + ~20% runtime overhead), not measured. MoE models load by total parameters.
| Precision | Est. Memory | Notes |
|---|---|---|
| FP16 (full precision) | ~281 GB | Best quality, highest memory usage |
| Q8 (8-bit quantized) | ~141 GB | Near-lossless quality, good balance |
| Q4 (4-bit quantized) | ~71 GB | Smallest footprint, slight quality loss |
Budget Picks
No sub-$1,000 box has the allocatable memory for this model at Q4 — see the mid-range and premium picks below.
Mid-Range Picks
Premium Picks
$5,299 — discontinued
- Chip: Apple M3 Ultra (28-core CPU / 60-core GPU, up to 32/80)
- Neural Engine: 32-core
- Unified Memory: 96GB (256/512GB configs discontinued 2026)
$6,950
- Chip: GB10 Grace Blackwell Superchip
- CPU: 20-core Arm (10× Cortex-X925 + 10× A725)
- GPU: Blackwell (5th-gen Tensor Cores), CUDA-native
$5,999 – $7,999
- Chip: GB10 Grace Blackwell Superchip
- CPU: 20-core Arm (10× Cortex-X925 + 10× A725)
- GPU: Blackwell (5th-gen Tensor Cores), CUDA-native
$4,349
- APU: AMD Ryzen AI Max+ 395 (16C/32T, Zen 5)
- GPU: Radeon 8060S (40 CU, RDNA 3.5)
- NPU: 50 TOPS (XDNA 2)
$5,349 – $7,406
- APU: AMD Ryzen AI Max+ PRO 395 (16C/32T, Zen 5, vPro)
- GPU: Radeon 8060S (40 CU, RDNA 3.5)
- NPU: 50 TOPS (XDNA 2)
$3,649
- APU: AMD Ryzen AI Max+ 395 (16C/32T, Zen 5)
- GPU: Radeon 8060S (40 CU, RDNA 3.5)
- NPU: 50 TOPS (XDNA 2)
$3,799
- APU: AMD Ryzen AI Max+ 395 (16C/32T, Zen 5)
- GPU: Radeon 8060S (40 CU, RDNA 3.5)
- NPU: 50 TOPS (XDNA 2)
$3,449
- APU: AMD Ryzen AI Max+ 395 (16C/32T, Zen 5)
- GPU: Radeon 8060S (40 CU, RDNA 3.5)
- NPU: 50 TOPS (XDNA 2)
Disclosure: Some links on this page are affiliate links. We may earn a commission if you make a purchase — at no extra cost to you. This helps support our independent reviews.