laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
Global Score
84 vs 95
Hardware Fit
100 vs 94
Quality Score
77 vs 96
Hardware
laguna-xs-2.1 qwen3-30b-a3b-thin…
MachineAZW GTR ProMac Studio
CPUAMD RYZEN AI MAX+ 395Apple M2 Max
Cores3212
RAM125 GB96 GB
GPURadeon 8060SApple M2 Max
OSUbuntu 24.04.4 LTSmacOS 26.1
Archx64arm64
Power Modelow-powerbalanced
Performance
laguna-xs-2.1 qwen3-30b-a3b-thin…
Tokens/sec65.980.4
First chunk281 ms46 ms
TTFT281 ms1.8 s
Load time9.9 sN/A
Memory usage30.1 GB21.2 GB
Memory %24%22%
HW Fit Score Breakdown
laguna-xs-2.1
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
Quality
laguna-xs-2.1
Reasoning
8/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest