| Model profile | ||
|---|---|---|
| Model | Size | Approximate size |
| Laguna S 2.1Model source: provider1,048,576 tokens max native context | 118Bactive 8B | 70.8 GB4-bit quantization |
| Compatible hardware Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone. | ||||
|---|---|---|---|---|
| Hardware | Memory | Bandwidth | vLLM | Estimated generation |
| Radeon 8060S 96GB | 96 GBUnified RAM | 256 GB/s | yes | 21 tok/s4-bit quantization |
| DGX Spark | 128 GBUnified RAM | 273 GB/s | yes | 23 tok/s4-bit quantization |
| M5 Max | 128 GBUnified RAM | 614 GB/s | no | 49 tok/s4-bit quantization |
| M3 Ultra | 96 GBUnified RAM | 819 GB/s | no | 64 tok/s4-bit quantization |
| M5 Ultra | 256 GBUnified RAM | 1200 GB/s | no | 90 tok/s4-bit quantization |
| RTX PRO 6000 | 96 GBGPU VRAM | 1792 GB/s | yes | 126 tok/s4-bit quantization |
| DGX H200 | 1128 GBGPU HBM3e | 4800 GB/s | yes | 257 tok/s4-bit quantization |
| DGX Station | 748 GBCoherent Memory | 7100 GB/s | yes | 321 tok/s4-bit quantization |
| ET900N G3 | 748 GBCoherent Memory | 7100 GB/s | yes | 321 tok/s4-bit quantization |
| DGX B200 | 1440 GBGPU HBM3e | 8000 GB/s | yes | 341 tok/s4-bit quantization |
| GB200 NVL72 | 13400 GBGPU HBM3e | 8000 GB/s | yes | 341 tok/s4-bit quantization |
| GB300 NVL72 | 20000 GBGPU HBM3e | 8000 GB/s | yes | 341 tok/s4-bit quantization |
Evaluates Laguna S 2.1 118B A8B against its XS version using Performance, Memory, Agency, OpenAI Human Eval, Sand Physics, Kanban, Dungeon Crawler, Blender and Godot tests.
Tests Laguna S-2.1, M.1 and Qwen3.6-27B via Grok Build and OpenCode on a Pi goal extension and Splunk CTF, evaluating coding quality, agentic behavior, reasoning, tool use, instruction following, loop
Compares Laguna S 2.1 and Qwen 3.6 35B-A3B on an RTX 3060 using llama.cpp, evaluating debugging accuracy and animation generation tasks via manual testing.
Tests Poolside Laguna S2.1 performance in browser workflows, C++ game creation, FPS development, creative writing, website design, fan fiction, 3D printer simulation, and frontend testing.
Tests Laguna S2.1 using Inferencer App v2.2.2 on M3 Ultra 512 GiB against DeepSeek and GLM based on benchmarks claiming superiority.
Tests Laguna S 2.1's real-world coding capabilities and benchmarks performance against GLM 5.2, Qwen 3.7 Max, Hy3, and Kimi K3 using Woaibench.
Installs and tests Laguna S 2.1, an 118B MoE model designed for software engineering and agentic coding use cases.