Qwen3-14B vs JiRackDeltaNet_27b

Specs, VRAM requirements and download trends — updated 24 October 2026.

Qwen · A · Open weights
Params
14.8 B
Context
40,960
30d
9.4 M
apache-2.0 · commercial OK
CMSManhattan · B · Open weights
Params
27.3 B
Context
262,144
30d
494 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-14B JiRackDeltaNet_27b
Deployment Open weights · also via API Open weights
Parameters 14.8 B 27.3 B
Architecture Qwen3ForCausalLM Qwen3_5ForCausalLM
Context length 40,960 262,144
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages — 13
Downloads 30d 9,401,416 494,347
Downloads all time 38.0 M 561 K
Quantizations on the Hub SAFETENSORS GGUF, SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2026-08-29
API input price / 1M tokens $0.12 not on OpenRouter
API output price / 1M tokens $0.24 not on OpenRouter
Est. cost per 1M input + 1M output tokens $0.36 not on OpenRouter
Cached input / 1M tokens — not on OpenRouter
AA Intelligence Index 6.7 not on OpenRouter
AA Coding Index — not on OpenRouter
AA Agentic Index — not on OpenRouter
Max output tokens 16,384 not on OpenRouter
API providers 2 not on OpenRouter
Tool calling Yes not on OpenRouter
Reasoning mode Yes not on OpenRouter

API cost

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

Qwen3-14B $0.36

Download trend

Daily snapshots, last 89 days (28 Jul – 24 Oct)

9.4 M494 K
Qwen3-14B JiRackDeltaNet_27b

VRAM side by side

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

JiRackDeltaNet_27b · Q4_K_M 23.1 GB / 24 GB
⚠️ Tight — reduce context
Qwen3-14B · fp16 35.2 GB / 24 GB
❌ Won’t fit
JiRackDeltaNet_27b · fp16 @ 256K ctx 191.7 GB / 24 GB
❌ Won’t fit

Adjacent comparisons