Qwen3.6-35B-A3B-NVFP4 vs POCKET-26B-GGUF
Specs, VRAM requirements and download trends — updated 10 November 2026.
nvidia · A · Open weights
Params
18.7 B
Context
—
30d
4.0 M
apache-2.0 · commercial OK
FINAL-Bench · B · Open weights
Params
26.0 B
Context
—
30d
234 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | POCKET-26B-GGUF |
|---|---|---|
| Parameters | 18.7 B | 26.0 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | — |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 3,971,809 | 234,467 |
| Downloads all time | 42.1 M | 924 K |
| Quantizations on the Hub | SAFETENSORS | GGUF |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2026-07-24 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
12.6 M186 K
Qwen3.6-35B-A3B-NVFP4
POCKET-26B-GGUF
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
POCKET-26B-GGUF · Q4_K_M
22.9 GB / 24 GB
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB