Qwen3.6-35B-A3B-FP8 vs gemma-4-26B-A4B-it-QAT-MLX-4bit
Specs, VRAM requirements and download trends — updated 28 July 2026.
lmstudio-community · B
Params
4.6 B
Context
—
30d
914 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-FP8 | gemma-4-26B-A4B-it-QAT-MLX-4bit |
|---|---|---|
| Parameters | 36.0 B | 4.6 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | Gemma4ForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 8,946,336 | 914,362 |
| Downloads all time | 24.7 M | 2.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-15 | 2026-06-04 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
8.9 M914 K
Qwen3.6-35B-A3B-FP8
gemma-4-26B-A4B-it-QAT-MLX-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gemma-4-26B-A4B-it-QAT-MLX-4bit · fp16
18.4 GB / 24 GB
Qwen3.6-35B-A3B-FP8 · fp16
47.1 GB / 24 GB