Qwen3.6-35B-A3B-NVFP4 vs deepseek-coder-7b-instruct-v1.5

Specs, VRAM requirements and download trends — updated 6 August 2026.

nvidia · A

Params

18.7 B

Context

—

30d

11.3 M

apache-2.0 · commercial OK

deepseek-ai · B

Params

6.9 B

Context

4,096

30d

599 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.6-35B-A3B-NVFP4	deepseek-coder-7b-instruct-v1.5
Parameters	18.7 B	6.9 B
Architecture	Qwen3_5MoeForConditionalGeneration	LlamaForCausalLM
Context length	—	4,096
Licence	apache-2.0	other
Commercial use	Allowed	Unknown
Languages	—	—
Downloads 30d	11,298,952	598,564
Downloads all time	19.7 M	2.3 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-05-27	2024-01-25

Daily snapshots, last 10 days (28 Jul – 6 Aug)

11.3 M484 K

Qwen3.6-35B-A3B-NVFP4 deepseek-coder-7b-instruct-v1.5

On RTX 4090 · 24 GB · 8K context unless noted

deepseek-coder-7b-instruct-v1.5 · fp16 16.7 GB / 24 GB

✅ Runs comfortably

Qwen3.6-35B-A3B-NVFP4 · fp16 29.1 GB / 24 GB

❌ Won’t fit