Qwen3.6-35B-A3B-NVFP4 vs llava-onevision-qwen2-7b-ov
Specs, VRAM requirements and download trends — updated 6 August 2026.
lmms-lab · B
Params
8.0 B
Context
32,768
30d
194 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | llava-onevision-qwen2-7b-ov |
|---|---|---|
| Parameters | 18.7 B | 8.0 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | LlavaQwenForCausalLM |
| Context length | — | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 2 |
| Downloads 30d | 11,298,952 | 194,138 |
| Downloads all time | 19.7 M | 3.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2024-06-29 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
11.3 M194 K
Qwen3.6-35B-A3B-NVFP4
llava-onevision-qwen2-7b-ov
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
llava-onevision-qwen2-7b-ov · fp16
19.4 GB / 24 GB
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB