DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF vs Kimi-K2-Instruct

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

moonshotai · B · Open weights

Params

1,026.5 B

Context

131,072

30d

277 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF	Kimi-K2-Instruct
Deployment	Open weights	Open weights · also via API
Parameters	763.2 B	1,026.5 B
Architecture	—	DeepseekV3ForCausalLM
Context length	—	131,072
Licence	mit	other
Commercial use	Allowed	Unknown
Languages	—	—
Downloads 30d	3,270,121	277,334
Downloads all time	3.3 M	4.7 M
Quantizations on the Hub	GGUF	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-10-23	2025-07-11
API input price / 1M tokens	not on OpenRouter	$0.57
API output price / 1M tokens	not on OpenRouter	$2.30
Est. cost per 1M input + 1M output tokens	not on OpenRouter	$2.87
Cached input / 1M tokens	not on OpenRouter	—
AA Intelligence Index	not on OpenRouter	—
AA Coding Index	not on OpenRouter	—
AA Agentic Index	not on OpenRouter	—
Max output tokens	not on OpenRouter	98,304
API providers	not on OpenRouter	1
Tool calling	not on OpenRouter	Yes
Reasoning mode	not on OpenRouter	No

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

Kimi-K2-Instruct $2.87

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

3.3 M162 K

DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF Kimi-K2-Instruct

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

Kimi-K2-Instruct · fp16 @ 128K ctx 3,596.1 GB / 24 GB

❌ Won’t fit