GPT OSS 20B RichardErkhov Heresy vs GPT OSS 20B Heretic Ara v3
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| GPT OSS 20B RichardErkhov Heresy | GPT OSS 20B Heretic Ara v3 | |
|---|---|---|
| Parameters | 21.5B | 1.8B |
| Context | 131K | 131K |
| Architecture | GptOssForCausalLM | GptOssForCausalLM |
| License | Apache 2.0 | Apache 2.0 |
| Downloads | 181 | 1.1K |
| Released | Feb 2026 | Mar 2026 |
VRAM by Quantization: GPT OSS 20B RichardErkhov Heresy vs GPT OSS 20B Heretic Ara v3
| Quantization | Bits | GPT OSS 20B RichardErkhov Heresy VRAM | GPT OSS 20B Heretic Ara v3 VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 9.5 GB | — |
| Q3_K_M | 3.90 | 10.9 GB | — |
| Q3_K_S | 3.50 | 9.8 GB | — |
| Q4_0 | 4.00 | 11.1 GB | — |
| Q4_K_M | 4.80 | 13.3 GB | — |
| Q5_K_M | 5.70 | 15.7 GB | — |
| Q6_K | 6.60 | 18.1 GB | — |
| Q8_0 | 8.00 | 21.9 GB | 2.2 GB |
Verdict
GPT OSS 20B Heretic Ara v3 needs less VRAM at IQ4_NL (1.4 GB vs 12.5 GB), so it fits on smaller GPUs. GPT OSS 20B Heretic Ara v3 is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, GPT OSS 20B RichardErkhov Heresy or GPT OSS 20B Heretic Ara v3?
At IQ4_NL, GPT OSS 20B RichardErkhov Heresy needs 12.5 GB and GPT OSS 20B Heretic Ara v3 needs 1.4 GB, so GPT OSS 20B Heretic Ara v3 is the lighter option to run locally.
- Which has a longer context window, GPT OSS 20B RichardErkhov Heresy or GPT OSS 20B Heretic Ara v3?
GPT OSS 20B RichardErkhov Heresy supports 131,072 tokens and GPT OSS 20B Heretic Ara v3 supports 131,072 tokens.
- What is the difference between GPT OSS 20B RichardErkhov Heresy and GPT OSS 20B Heretic Ara v3?
GPT OSS 20B RichardErkhov Heresy is a 21.5B model from MuXodious (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.