MODEL · OPENAI · 21B TOTAL / 3.6B ACTIVE
gpt-oss-20b
OpenAI's open-weights MoE. Matches o3-mini on common benchmarks, post-trained with MXFP4 quantization so it lands in 16 GB VRAM — a near-frontier reasoner you can actually run on a 5060 Ti.
License: Apache 2.0 · Context: 128K · Released: August 2025
The decision in five lines
- The call
- Buy — for coding
- Best for
- coding · chat · agents
- Runs on
- 16 hardware picks fit (cheapest: Minisforum UM890 Pro · $463 barebone (no RAM / SSD); $991 with 32 GB / 1 TB — Minisforum US store, Sep 15 2026)
- Watch out
- When you want a "classic" dense 20B for fine-tuning — MoE fine-tunes are tricky, and the MXFP4 format means not every fine-tuning framework supports it out of the box.
- Evidence
- Measured
- 21B total
- PARAMETERS
- MOE
- TYPE
- 128K
- CONTEXT
- ~16 GB (native MXFP4)
- VRAM AT Q4
Where we recommend this
Every tier slot in the planner where this model is a top or alternate pick. Pulled live from planner.js — when the planner refreshes, this table stays current.
The call
OpenAI's open-weights MoE. Matches o3-mini on common benchmarks, post-trained with MXFP4 quantization so it lands in 16 GB VRAM — a near-frontier reasoner you can actually run on a 5060 Ti.
When not to use: When you want a "classic" dense 20B for fine-tuning — MoE fine-tunes are tricky, and the MXFP4 format means not every fine-tuning framework supports it out of the box.
Runner notes
Ollama tag `gpt-oss:20b`. Configurable reasoning effort (low/medium/high) is an in-prompt parameter — see OpenAI's docs for syntax. Drop-in replacement for older Mistral 7B / Qwen 2.5 14B workflows.
Hardware that fits
Every hardware pick whose memory fits this model at the quant we recommend. Sorted cheapest-first — the top row is your best-value fit. Click through for the full buyer’s guide.
- Minisforum UM890 ProGood · 1.4× 32 GB DDR5 (shared) · $463 barebone (no RAM / SSD); $991 with 32 GB / 1 TB — Minisforum US store, Sep 15 2026
- NVIDIA RTX 3090 (used, single)Good · 1.4× 24 GB · $950–$1,200
- AMD Radeon RX 7900 XTXGood · 1.4× 24 GB · $1,300–$1,500 new (no refurb in stock Sep 15 2026)
- MacBook Air M5 24 GBRequires tweak · 1.2× 24 GB unified · $1,499–$1,899
- Mac Mini M4 Pro 24 GBRequires tweak · 1.2× 24 GB unified · $1,699 (M5 Pro successor, 24 GB / 512 GB, pre-order; M4 Pro discontinued Aug 25 2026)
- Dual RTX 3090 (used)Perfect · 2.7× 48 GB · $1,800–$2,500 all-in
- NVIDIA RTX 4090Good · 1.4× 24 GB · $2,200–$2,800
- M5 Pro MacBook Pro 48 GBPerfect · 1.8× 48 GB unified · $2,999–$3,599
- Framework Desktop (Ryzen AI Max+ 395)Perfect · 4.8× 128 GB unified · $3,449 (128 GB config)
- NVIDIA RTX A6000 (48 GB, used)Perfect · 2.7× 48 GB ECC · $3,500–$4,500
- Mac Studio M4 Max 64 GBPerfect · 2.4× 64 GB unified · $3,799 (M5 Max successor, 64 GB / 1 TB, pre-order; M4 Max discontinued Aug 25 2026)
- NVIDIA DGX SparkPerfect · 4.8× 128 GB unified · $4,699
- M5 Max MacBook Pro 64 GBPerfect · 2.4× 64 GB unified · ~$5,199 (est.; June 25 2026 increase)
- Mac Studio M3 Ultra 96 GBPerfect · 3.6× 96 GB unified · $5,499 (M5 Ultra successor, 96 GB / 1 TB, pre-order; M3 Ultra discontinued Aug 25 2026)
- NVIDIA RTX 5090Perfect · 1.8× 32 GB · $6,450–$7,000 (new, in stock)
- Dual RTX 5090Perfect · 3.6× 64 GB (2×32) · $13,300–$14,000 all-in (two cards alone are ~$12,900 at the Sep 15 2026 Newegg floor)
Next step
Find-by-model — see what hardware runs this→