Can I run gpt-oss-120b on an RTX 5080 (16GB)?
Computed with the open FitLLM engine — accurate per-layer KV-cache modeling, not a naive estimate. Updated 2026-07-10.
Memory breakdown (Q4_K_M, F16 KV, 33K context)
| Model weights | 66.7 GB |
| KV cache | 1.1 GB |
| Runtime overhead + reserve | 11.2 GB |
| Total used | 78.9 / 16 GB |
| Short by | 62.9 GB |
Max context that fits at Q4_K_M: does not fit.
Every quantization on the RTX 5080
| Weight quant | Weights | Fits (KV F16) | Used @32K |
|---|---|---|---|
| Q4_K_M | 66.7 GB | ❌ won't fit | 78.9 / 16.0 GB |
| Q5_K_M | 77.7 GB | ❌ won't fit | 91.3 / 16.0 GB |
| Q6_K | 89.4 GB | ❌ won't fit | 104 / 16.0 GB |
| Q8_0 | 116 GB | ❌ won't fit | 134 / 16.0 GB |
| FP16 | 218 GB | ❌ won't fit | 248 / 16.0 GB |
Lower weight quants free memory at some output-quality cost — Q4 is the common sweet spot; below that quality drops faster.
KV cache is F16 here (llama.cpp default). Drop it to Q8/Q4 (-ctk/-ctv) for more context.
Embed this verdict
Live badge for your README or model card — recomputed by the engine, never stale:
[](https://fitllm.run/can-i-run/gpt-oss-120b-on-rtx-5080)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "gpt-oss-120b" --gpu "RTX 5080"Why most VRAM calculators get this wrong
gpt-oss-120b interleaves sliding-window (local) and global attention 5:1. The local layers cap their KV cache at the 128-token window, and the global layers use a different head shape (head_dim 64 vs 64). A naive "all layers × full context × one head_dim" formula over-counts KV cache by several times.
What fits on the RTX 5080 instead
same GPU Models that fit on the RTX 5080: Gemma 4 e2b, Gemma 4 e4b, Gemma 4 12b, Llama-3.2-3B-Instruct, Llama-3.1-8B-Instruct, Qwen3-0.6B, Qwen3-1.7B, Llama-3.2-1B-Instruct, Gemma-3-1B-it.
same model GPUs that run gpt-oss-120b: RTX PRO 6000 Blackwell (96GB), 4× RTX 3090 (96GB), H200 141GB (141GB), B200 (192GB).
Reproduce it
gpt-oss-120b = 117B (5.1B active, MoE), 36 layers. The RTX 5080 has 16GB / 960GB/s. Same math, open source: fitllm-engine. GGUF bpw from llama.cpp.
All numbers are computed by the open-source fitllm-engine (MIT) from official model config.json values — reproduce or audit them yourself. Estimates; real usage varies with runtime (llama.cpp / MLX / Ollama), driver and display. Found a mismatch? Report it. · FitLLM home