qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
Global Score
70 vs 84
Hardware Fit
93 vs 64
Quality Score
60 vs 92
Hardware
qwen3.5-2b-mlx unsloth/gemma-4-26…
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-2b-mlx unsloth/gemma-4-26…
Tokens/sec32.916.5
First chunk3096 ms32 ms
TTFT3.1 s2.2 s
Load timeN/AN/A
Memory usage2.5 GB19.3 GB
Memory %8%80%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
unsloth/gemma-4-26b-a4b…
Speed
36/50
TTFT
18/20
Memory
10/30
Quality
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
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