Llama-3.1-8B-Instruct vs gpt-oss-20b-MXFP4-Q8
Specs, VRAM requirements and download trends — updated 6 August 2026.
mlx-community · B
Params
20.9 B
Context
131,072
30d
355 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.1-8B-Instruct | gpt-oss-20b-MXFP4-Q8 |
|---|---|---|
| Parameters | 8.0 B | 20.9 B |
| Architecture | LlamaForCausalLM | GptOssForCausalLM |
| Context length | — | 131,072 |
| Licence | llama3.1 | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | 8 | — |
| Downloads 30d | 8,014,793 | 355,273 |
| Downloads all time | 175.3 M | 7.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-18 | 2025-08-29 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
8.0 M346 K
Llama-3.1-8B-Instruct
gpt-oss-20b-MXFP4-Q8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.1-8B-Instruct · fp16
19.4 GB / 24 GB
gpt-oss-20b-MXFP4-Q8 · fp16 @ 128K ctx
64.0 GB / 24 GB