gpt-oss-20b vs Qwen3-Coder-30B-A3B-Instruct-MLX-4bit
Specs, VRAM requirements and download trends — updated 5 August 2026.
lmstudio-community · B
Params
30.5 B
Context
262,144
30d
156 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-20b | Qwen3-Coder-30B-A3B-Instruct-MLX-4bit |
|---|---|---|
| Parameters | 21.5 B | 30.5 B |
| Architecture | GptOssForCausalLM | Qwen3MoeForCausalLM |
| Context length | 131,072 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 6,658,531 | 156,307 |
| Downloads all time | 98.5 M | 2.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-04 | 2025-07-31 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
8.6 M156 K
gpt-oss-20b
Qwen3-Coder-30B-A3B-Instruct-MLX-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt-oss-20b · fp16 @ 128K ctx
82.4 GB / 24 GB
Qwen3-Coder-30B-A3B-Instruct-MLX-4bit · fp16 @ 256K ctx
165.9 GB / 24 GB