Model Spend Arena2ND ED.
22B · MoE · 131,072 ctx · 2026-08-14

gpt-oss-20b

Runs on ≤16 GB · Hugging Face ↗

llama.cppvLLMOllamaLM Studio

Coding index 20.7 (Artificial Analysis)

OpenAI's open-weight 20B, shipped natively in MXFP4 (~4-bit) — so its on-disk size already IS the quantized size. Uses the "harmony" chat format with separate reasoning channels.

First-party test · not the AA coding index

HumanEval pass@1 97% (29/30), via local GPU (Ollama, Q4_K_M). Measured by us on this hardware, as a rough sanity check — HumanEval is a different, easier, partly-contaminated benchmark than Artificial Analysis’ composite, so it is not comparable to the coding-index column.

First-party test · not the AA coding index

BigCodeBench-Hard pass@1 26% (31/121), via local GPU (Ollama, MXFP4). The brutal counterpart to HumanEval — where HumanEval saturates near the top, BCB-Hard spreads the field, so this is the number that actually separates coding ability.

First-party measurement

~61 tok/s on RTX 4060 Ti, measured by us.

Sizes on disk

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

QuantizationSize
Q8_00.9 GB
BF161.7 GB
MXFP412.1 GB

Config tips

Do NOT re-quantize — it is already 4-bit; a Q8 re-quant only wastes VRAM. Fits ~13 GB. Needs a runtime with MXFP4 support (recent llama.cpp / vLLM / Ollama). Set the reasoning effort via the harmony system fields.