gemma-3-270m-it-qat-mlx
LM-STUDIO MLXgemma3_text · 270M · 4bit
Mar 4, 2026 · Apple M4
qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
OPENAI GGUFApr 21, 2026 · Apple M2 Max
Global Score
43 vs 62
Hardware Fit
99 vs 100
Quality Score
19 vs 45
Hardware
gemma-3-270m-it-qa… qwen3.5-35b-a3b-un…
MachineMacBook AirMac Studio
CPUApple M4Apple M2 Max
Cores1012
RAM32 GB96 GB
GPUApple M4Apple M2 Max
OSmacOS 26.3macOS 26.1
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma-3-270m-it-qa… qwen3.5-35b-a3b-un…
Tokens/sec344.267.9
First chunk173 ms50 ms
TTFT173 ms75 ms
Load timeN/A0.0 s
Memory usage0.3 GB0.0 GB
Memory %1%0%
HW Fit Score Breakdown
gemma-3-270m-it-qat-mlx
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma-3-270m-it-qat-mlx
Reasoning
4/20
Coding
0/20
Instruction
9/20
Structured
3/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
qwen3.5-35b-a3b-uncenso…
Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
0/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor 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