gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 23, 2026 · Apple M1 Pro
Global Score
78 vs 61
Hardware Fit
72 vs 97
Quality Score
81 vs 46
Hardware
gemma4:e4b-mlx hf.co/LiquidAI/LFM…
MachineMacBook ProMacBook Pro
CPUApple M2 ProApple M1 Pro
Cores1010
RAM16 GB16 GB
GPUApple M2 ProApple M1 Pro
OSmacOS 26.5macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:e4b-mlx hf.co/LiquidAI/LFM…
Tokens/sec26.931.4
First chunk222 ms138 ms
TTFT222 ms138 ms
Load time0.1 s3.7 s
Memory usage15.4 GB6.6 GB
Memory %96%41%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
gemma4:e4b-mlx
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
hf.co/LiquidAI/LFM2.5-2…
Reasoning
14/20
Coding
13/20
Instruction
3/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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