gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
tinyllama-1.1b-chat-v1.0
LM-STUDIO GGUFllama · 1.1B · Q3_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
76 vs 33
Hardware Fit
46 vs 76
Quality Score
89 vs 14
Hardware
gemma4:31b tinyllama-1.1b-cha…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M4 MaxIntel Core™ i5-5300U
Cores164
RAM64 GB16 GB
GPUApple M4 MaxIntel(R) HD Graphics 5500
OSmacOS 26.3.1Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:31b tinyllama-1.1b-cha…
Tokens/sec22.49.9
First chunk565 ms3166 ms
TTFT30.0 s3.2 s
Load time6.9 sN/A
Memory usage43.9 GB0.5 GB
Memory %69%3%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
tinyllama-1.1b-chat-v1.0
Speed
32/50
TTFT
16/20
Memory
28/30
Quality
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
tinyllama-1.1b-chat-v1.0
Reasoning
2/20
Coding
1/20
Instruction
6/20
Structured
2/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor 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