DeepSeek-V3-0324 vs DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

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

deepseek-ai · A · Open weights

Params

684.5 B

Context

163,840

30d

150 K

mit · commercial OK

ISTA-DASLab · B · Open weights

Params

763.2 B

Context

—

30d

3.3 M

mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	DeepSeek-V3-0324	DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
Deployment	Open weights · also via API	Open weights
Parameters	684.5 B	763.2 B
Architecture	DeepseekV3ForCausalLM	—
Context length	163,840	—
Licence	mit	mit
Commercial use	Allowed	Allowed
Languages	—	—
Downloads 30d	149,937	3,270,121
Downloads all time	10.5 M	3.3 M
Quantizations on the Hub	SAFETENSORS	GGUF
Gated	No	No
First seen on the Hub	2025-03-24	2026-10-23
API input price / 1M tokens	$0.29	not on OpenRouter
API output price / 1M tokens	$1.14	not on OpenRouter
Est. cost per 1M input + 1M output tokens	$1.43	not on OpenRouter
Cached input / 1M tokens	$0.11	not on OpenRouter
AA Intelligence Index	—	not on OpenRouter
AA Coding Index	21.2	not on OpenRouter
AA Agentic Index	0.8	not on OpenRouter
Max output tokens	115,200	not on OpenRouter
API providers	2	not on OpenRouter
Tool calling	Yes	not on OpenRouter
Reasoning mode	No	not on OpenRouter

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

DeepSeek-V3-0324 $1.43

Daily snapshots, last 90 days (13 Aug – 10 Nov)

3.3 M150 K

DeepSeek-V3-0324 DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

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

DeepSeek-V3-0324 · fp16 @ 160K ctx 2,811.5 GB / 24 GB

❌ Won’t fit