DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF vs Step-5-Preview

Specs, VRAM requirements and download trends — updated 10 November 2026.

ISTA-DASLab · A · Open weights

Params

763.2 B

Context

—

30d

3.3 M

mit · commercial OK

stepfun-ai · B · Open weights

Params

604.3 B

Context

—

30d

7 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF	Step-5-Preview
Deployment	Open weights	Open weights · also via API
Parameters	763.2 B	604.3 B
Architecture	—	Step5ForConditionalGeneration
Context length	—	1,000,000
Licence	mit	other
Commercial use	Allowed	Unknown
Languages	—	—
Downloads 30d	3,270,121	7,411
Downloads all time	3.3 M	7 K
Quantizations on the Hub	GGUF	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-10-23	2026-09-20
API input price / 1M tokens	not on OpenRouter	$1.00
API output price / 1M tokens	not on OpenRouter	$2.70
Est. cost per 1M input + 1M output tokens	not on OpenRouter	$3.70
Cached input / 1M tokens	not on OpenRouter	$0.10
AA Intelligence Index	not on OpenRouter	28.5
AA Coding Index	not on OpenRouter	—
AA Agentic Index	not on OpenRouter	—
Max output tokens	not on OpenRouter	64,000
API providers	not on OpenRouter	2
Tool calling	not on OpenRouter	Yes
Reasoning mode	not on OpenRouter	Yes

Estimated cost of 1M input + 1M output tokens via OpenRouter

Step-5-Preview $3.70

Daily snapshots, last 16 days (26 Oct – 10 Nov)

3.3 M1 K

DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF Step-5-Preview

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

Step-5-Preview · fp16 806.5 GB / 24 GB

❌ Won’t fit