Qwen3-Coder-Next-FP8-dynamic vs Laguna-S-2.1-NVFP4
Specs, VRAM requirements and download trends — updated 14 August 2026.
RedHatAI · A · Open weights
Params
79.8 B
Context
262,144
30d
170 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Coder-Next-FP8-dynamic | Laguna-S-2.1-NVFP4 |
|---|---|---|
| Parameters | 79.8 B | 117.6 B |
| Architecture | Qwen3NextForCausalLM | LagunaForCausalLM |
| Context length | 262,144 | 1,048,576 |
| Licence | apache-2.0 | openmdw-1.1 |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 169,988 | 191,685 |
| Downloads all time | 1.2 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-27 | 2026-07-02 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
864 K170 K
Qwen3-Coder-Next-FP8-dynamic
Laguna-S-2.1-NVFP4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Coder-Next-FP8-dynamic · fp16 @ 256K ctx
473.2 GB / 24 GB
Laguna-S-2.1-NVFP4 · fp16 @ 1024K ctx
2,367.3 GB / 24 GB