gemma4:e4b
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
codellama:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
84 vs 63
Hardware Fit
98 vs 97
Quality Score
78 vs 49
Hardware
gemma4:e4b codellama:7b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
gemma4:e4b codellama:7b
Tokens/sec53.023.6
First chunk214 msN/A
TTFT214 ms297 ms
Load time3.1 s0.9 s
Memory usage15.0 GB12.6 GB
Memory %12%39%
HW Fit Score Breakdown
gemma4:e4b
Speed
48/50
TTFT
20/20
Memory
30/30
codellama:7b
Speed
37/50
TTFT
30/20
Memory
30/30
Quality
gemma4:e4b
Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
codellama:7b
Reasoning
6/20
Coding
7/20
Instruction
12/20
Structured
13/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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