Can I run gpt-oss-120b on my PC?
gpt-oss 120B (117B, 5.8B active) needs about 59.5 GB of GPU memory at 4-bit with an 8K context. No single consumer GPU we track runs it fully in VRAM at 4-bit. With llama.cpp offload, the smallest card that can run it is the RX 7600 with 64 GB of system RAM, at an estimated 12.0–22.9 tokens/sec (usable for chat). The smallest Mac that runs it is the Mac M2 Max 96GB.
gpt-oss 120B on every GPU and Mac
Best quant that fits fully in memory at 8K context with a speed ceiling; otherwise the llama.cpp offload plan (system RAM needed, estimated speed from DDR4-3200 to DDR5-6000). Macs and unified-memory PCs share one pool, so offload adds nothing there. How offload is estimated.
| Hardware | Memory | Verdict | Details |
|---|---|---|---|
| RX 7600 | 8 GB | Offload Q4_K_M, 64 GB RAM · ~12–23 tok/s | details |
| RTX 4060 | 8 GB | Offload Q4_K_M, 64 GB RAM · ~12–23 tok/s | details |
| RTX 5060 | 8 GB | Offload Q4_K_M, 64 GB RAM · ~12–24 tok/s | details |
| RTX 3060 Ti | 8 GB | Offload Q4_K_M, 64 GB RAM · ~12–24 tok/s | details |
| RTX 4060 Ti 8GB | 8 GB | Offload Q4_K_M, 64 GB RAM · ~12–23 tok/s | details |
| RTX 3070 | 8 GB | Offload Q4_K_M, 64 GB RAM · ~12–24 tok/s | details |
| RTX 3080 10GB | 10 GB | Offload Q4_K_M, 64 GB RAM · ~13–26 tok/s | details |
| Arc B580 | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–25 tok/s | details |
| RTX 3060 12GB | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–25 tok/s | details |
| RX 7700 XT | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–25 tok/s | details |
| RTX 5070 | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–27 tok/s | details |
| RTX 4070 | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–26 tok/s | details |
| RTX 4070 Super | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–26 tok/s | details |
| RTX 4070 Ti | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–26 tok/s | details |
| RTX 3080 12GB | 12 GB | Offload Q4_K_M, 64 GB RAM · ~13–27 tok/s | details |
| Arc A770 16GB | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–27 tok/s | details |
| RTX 5060 Ti 16GB | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–27 tok/s | details |
| RTX 4060 Ti 16GB | 16 GB | Offload Q4_K_M, 64 GB RAM · ~13–25 tok/s | details |
| RX 7800 XT | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s | details |
| RX 7900 GRE | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s | details |
| RX 9070 | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s | details |
| RX 9070 XT | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s | details |
| RTX 5070 Ti | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–29 tok/s | details |
| RTX 4070 Ti Super | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s | details |
| RTX 4080 Super | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s | details |
| RTX 5080 | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–29 tok/s | details |
| RTX 4080 | 16 GB | Offload Q4_K_M, 64 GB RAM · ~14–28 tok/s | details |
| RX 7900 XT | 20 GB | Offload Q4_K_M, 64 GB RAM · ~16–31 tok/s | details |
| RX 7900 XTX | 24 GB | Offload Q4_K_M, 64 GB RAM · ~17–34 tok/s | details |
| RTX 3090 | 24 GB | Offload Q4_K_M, 64 GB RAM · ~17–34 tok/s | details |
| RTX 4090 | 24 GB | Offload Q4_K_M, 64 GB RAM · ~17–34 tok/s | details |
| RTX 3090 Ti | 24 GB | Offload Q4_K_M, 64 GB RAM · ~17–34 tok/s | details |
| RTX 5090 | 32 GB | Offload Q4_K_M, 64 GB RAM · ~22–44 tok/s | details |
| DGX Spark | 128 GB | F16 · ~85 tok/s | details |
| Ryzen AI Max+ 395 128GB | 128 GB | F16 · ~80 tok/s | details |
| Mac M1 16GB | 16 GB | No | details |
| Mac M4 16GB | 16 GB | No | details |
| Mac M2 24GB | 24 GB | No | details |
| Mac M3 24GB | 24 GB | No | details |
| Mac M4 Pro 24GB | 24 GB | No | details |
| Mac M4 32GB | 32 GB | No | details |
| Mac M1 Pro 32GB | 32 GB | No | details |
| Mac M3 Pro 36GB | 36 GB | No | details |
| Mac M4 Pro 48GB | 48 GB | No | details |
| Mac M4 Pro 64GB | 64 GB | No | details |
| Mac M1 Max 64GB | 64 GB | No | details |
| Mac M4 Max 64GB | 64 GB | No | details |
| Mac M2 Max 96GB | 96 GB | F16 · ~124 tok/s | details |
| Mac M3 Max 128GB | 128 GB | F16 · ~124 tok/s | details |
| Mac M4 Max 128GB | 128 GB | F16 · ~170 tok/s | details |
| Mac M2 Ultra 192GB | 192 GB | F16 · ~249 tok/s | details |
| Mac M3 Ultra 256GB | 256 GB | F16 · ~255 tok/s | details |
| Mac M3 Ultra 512GB | 512 GB | F16 · ~255 tok/s | details |
Questions
How much VRAM do I need for gpt-oss 120B?
About 59.5 GB at 4-bit (Q4_K_M) with an 8K context, including KV cache and runtime overhead. Longer contexts need more; the model page has the full table by quant and context.
Why can a mixture-of-experts model run on a smaller card?
Only 5.8B of its 117B parameters are used per token. llama.cpp's --n-cpu-moe keeps the expert weights of some layers in system RAM while attention and the KV cache stay on the GPU, so each token reads far less from slow RAM than a dense model of the same size would.
Other popular checks: Can I run gpt-oss-20b?Can I run Llama 70B?Can I run Qwen3?Can I run DeepSeek R1? · Best GPU by budget · Mac vs PC
Model data: Hugging Face Hub API and GGUF file sizes. GPU specs: vendor pages. Speeds are estimates, not benchmarks. Methodology · Report an error.