codegemma:7b
OLLAMA GGUFgemma · 9B · Q4_0
Mar 1, 2026 · Apple M4
hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 26, 2026 · Apple M1 Pro
Global Score
71 vs 61
Hardware Fit
91 vs 97
Quality Score
62 vs 46
Hardware
codegemma:7b hf.co/LiquidAI/LFM…
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
codegemma:7b hf.co/LiquidAI/LFM…
Tokens/sec18.731.3
First chunkN/A131 ms
TTFT320 ms131 ms
Load time0.8 s4.2 s
Memory usage8.7 GB6.6 GB
Memory %27%41%
HW Fit Score Breakdown
codegemma:7b
Speed
31/50
TTFT
30/20
Memory
30/30
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
codegemma:7b
Reasoning
1/20
Coding
14/20
Instruction
13/20
Structured
15/15
Math
10/15
Multilingual
9/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate 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