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
gemma-4-e2b-it@q5_k_xl
LM-STUDIO GGUFgemma4 · Q5_K_XL
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
95 vs 79
Hardware Fit
94 vs 81
Quality Score
96 vs 78
Hardware
qwen3-30b-a3b-thin… gemma-4-e2b-it@q5_…
MachineMac StudioDocker Container
CPUApple M2 MaxIntel Gen Intel® Core™ i9-11900H
Cores1216
RAM96 GB15 GB
GPUApple M2 MaxTigerLake-H GT1 [UHD Graphics]
OSmacOS 26.1Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen3-30b-a3b-thin… gemma-4-e2b-it@q5_…
Tokens/sec80.417.2
First chunk46 ms7 ms
TTFT1.8 s1.6 s
Load timeN/A8.9 s
Memory usage21.2 GB0.0 GB
Memory %22%0%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
gemma-4-e2b-it@q5_k_xl
Speed
32/50
TTFT
19/20
Memory
30/30
Quality
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
gemma-4-e2b-it@q5_k_xl
Reasoning
11/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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