unsloth/gemma-4-26b-a4b-it@q4_k_m
LM-STUDIO GGUFgemma4 · 26B · Q4_K_M
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
llama3:latest
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
83 vs 71
Hardware Fit
58 vs 95
Quality Score
93 vs 60
Hardware
unsloth/gemma-4-26… llama3:latest
MachineDocker ContainerMacBook Air
CPUIntel Gen Intel® Core™ i9-11900HApple M4
Cores1610
RAM15 GB32 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4
OSUbuntu 26.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
unsloth/gemma-4-26… llama3:latest
Tokens/sec9.422.3
First chunk42 msN/A
TTFT4.1 s295 ms
Load time44.3 s0.8 s
Memory usage0.2 GB5.6 GB
Memory %1%18%
HW Fit Score Breakdown
unsloth/gemma-4-26b-a4b…
Speed
17/50
TTFT
11/20
Memory
30/30
llama3:latest
Speed
35/50
TTFT
30/20
Memory
30/30
Quality
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3:latest
Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak 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