Model Spend Arena2ND ED.
117B · MoE · 131,072 ctx · 2026-08-14

gpt-oss-120b

Runs on ≤80 GB · Hugging Face ↗

vLLMllama.cppOllama

Coding index 30.4 (Artificial Analysis)

The larger open-weight OpenAI model, also MXFP4-native. ~63 GB at its shipped precision — a single 80 GB card (H100/A100) or a 2×48 GB / 2×40 GB split.

Sizes on disk

Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈2 GB at 32K, fp16).

QuantizationSize
Q4_062.6 GB
Q3_K_M62.6 GB
Q4_162.7 GB
Q4_K_S62.8 GB
Q4_K_M62.8 GB
Q5_K_M62.9 GB
Q463.0 GB
Q8_063.4 GB
Q864.5 GB
F1665.4 GB
Q2_K125.4 GB
Q6_K126.6 GB

Config tips

Not a consumer-GPU model — plan for 80 GB or multi-GPU. MXFP4-native, so don't re-quantize. vLLM gives the best throughput; llama.cpp works with CPU/GPU offload if you are short on VRAM (slower).