Qwen2.5-3B-Instruct vs medgemma-27b-text-it-GPTQ
Specs, VRAM requirements and download trends — updated 25 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-3B-Instruct | medgemma-27b-text-it-GPTQ |
|---|---|---|
| Parameters | 3.1 B | 4.8 B |
| Architecture | Qwen2ForCausalLM | Gemma3ForCausalLM |
| Context length | 32,768 | 131,072 |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | 1 | 1 |
| Downloads 30d | 3,718,369 | 202,049 |
| Downloads all time | 124.5 M | 341 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2026-04-03 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
7.6 M188 K
Qwen2.5-3B-Instruct
medgemma-27b-text-it-GPTQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-3B-Instruct · fp16
7.8 GB / 24 GB
medgemma-27b-text-it-GPTQ · fp16 @ 128K ctx
29.7 GB / 24 GB