dolphin-2.9.1-yi-1.5-34b vs Laguna-S-2.1

Specs, VRAM requirements and download trends — updated 23 October 2026.

dphn · A · Open weights
Params
34.4 B
Context
8,192
30d
4.6 M
apache-2.0 · commercial OK
poolside · B · Open weights
Params
117.6 B
Context
1,048,576
30d
397 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification dolphin-2.9.1-yi-1.5-34b Laguna-S-2.1
Deployment Open weights Open weights · also via API
Parameters 34.4 B 117.6 B
Architecture LlamaForCausalLM LagunaForCausalLM
Context length 8,192 1,048,576
Licence apache-2.0 openmdw-1.1
Commercial use Allowed Unknown
Languages — —
Downloads 30d 4,609,570 397,257
Downloads all time 82.9 M 552 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-05-18 2026-07-13
API input price / 1M tokens not on OpenRouter $0.09
API output price / 1M tokens not on OpenRouter $0.18
Est. cost per 1M input + 1M output tokens not on OpenRouter $0.27
Cached input / 1M tokens not on OpenRouter $0.009
AA Intelligence Index not on OpenRouter —
AA Coding Index not on OpenRouter —
AA Agentic Index not on OpenRouter —
Max output tokens not on OpenRouter 131,072
API providers not on OpenRouter 1
Tool calling not on OpenRouter Yes
Reasoning mode not on OpenRouter Yes

API cost

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

Laguna-S-2.1 $0.27

Download trend

Daily snapshots, last 88 days (28 Jul – 23 Oct)

4.8 M190 K
dolphin-2.9.1-yi-1.5-34b Laguna-S-2.1

VRAM side by side

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

dolphin-2.9.1-yi-1.5-34b · fp16 81.3 GB / 24 GB
❌ Won’t fit
Laguna-S-2.1 · fp16 @ 1024K ctx 2,516.3 GB / 24 GB
❌ Won’t fit

Adjacent comparisons