Qwen3.6-35B-A3B-NVFP4 vs bge-reranker-v2.5-gemma2-lightweight-gptq
Specs, VRAM requirements and download trends — updated 20 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | bge-reranker-v2.5-gemma2-lightweight-gptq |
|---|---|---|
| Parameters | 18.7 B | 9.2 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | CostWiseGemmaForCausalLM |
| Context length | — | 8,192 |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 8,277,959 | 533,952 |
| Downloads all time | 34.5 M | 534 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2024-09-13 |
Download trend
Daily snapshots, last 55 days (28 Jul – 20 Sep)
12.6 M256 K
Qwen3.6-35B-A3B-NVFP4
bge-reranker-v2.5-gemma2-lightweight-gptq
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
bge-reranker-v2.5-gemma2-lightweight-gptq · fp16
8.7 GB / 24 GB
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB