GPT OSS 120B vs GPT OSS 20B Heretic Ara v3
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GPT OSS 120B | GPT OSS 20B Heretic Ara v3 | |
|---|---|---|
| Parameters | 120.4B | 1.8B |
| Context | 131K | 131K |
| Architecture | GptOssForCausalLM | GptOssForCausalLM |
| License | Apache 2.0 | Apache 2.0 |
| Downloads | 4.5M | 1.1K |
| Released | Aug 2025 | Mar 2026 |
VRAM by Quantization: GPT OSS 120B vs GPT OSS 20B Heretic Ara v3
| Quantization | Bits | GPT OSS 120B VRAM | GPT OSS 20B Heretic Ara v3 VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 51.6 GB | — |
| Q3_K_M | 3.90 | 59.1 GB | — |
| Q3_K_S | 3.50 | 53.1 GB | — |
| Q4_0 | 4.00 | 60.6 GB | — |
| Q4_K_M | 4.80 | 72.7 GB | — |
| Q5_K_M | 5.70 | 86.2 GB | — |
| Q6_K | 6.60 | 99.8 GB | — |
| Q8_0 | 8.00 | 120.8 GB | 2.2 GB |
Verdict
GPT OSS 20B Heretic Ara v3 needs less VRAM at Q8_0 (2.2 GB vs 120.8 GB), so it fits on smaller GPUs. GPT OSS 120B is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, GPT OSS 120B or GPT OSS 20B Heretic Ara v3?
At Q8_0, GPT OSS 120B needs 120.8 GB and GPT OSS 20B Heretic Ara v3 needs 2.2 GB, so GPT OSS 20B Heretic Ara v3 is the lighter option to run locally.
- Which has a longer context window, GPT OSS 120B or GPT OSS 20B Heretic Ara v3?
GPT OSS 120B supports 131,072 tokens and GPT OSS 20B Heretic Ara v3 supports 131,072 tokens.
- What is the difference between GPT OSS 120B and GPT OSS 20B Heretic Ara v3?
GPT OSS 120B is a 120.4B model from OpenAI (GPT-OSS family), while GPT OSS 20B Heretic Ara v3 is a 1.8B model from p-e-w (GPT-OSS family). Compare their VRAM requirements above to see which fits your GPU or Mac.