Qwen3.6-35B-A3B-NVFP4 vs DeepSeek-R1-Distill-Llama-70B
Specs, VRAM requirements and download trends — updated 5 September 2026.
nvidia · A · Open weights
Params
18.7 B
Context
—
30d
4.0 M
apache-2.0 · commercial OK
deepseek-ai · B · Open weights
Params
70.6 B
Context
131,072
30d
189 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| Parameters | 18.7 B | 70.6 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | LlamaForCausalLM |
| Context length | — | 131,072 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 3,971,809 | 189,344 |
| Downloads all time | 42.1 M | 5.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2025-01-20 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
12.6 M189 K
Qwen3.6-35B-A3B-NVFP4
DeepSeek-R1-Distill-Llama-70B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB
DeepSeek-R1-Distill-Llama-70B · fp16 @ 128K ctx
325.0 GB / 24 GB