gemma-4-26b-a4b-it@iq3_xxs
LM-STUDIO GGUFgemma4 · 26B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
qwen2.5-1.5b-instruct
LM-STUDIO MLXqwen2 · 1.5B · 8bit
Mar 4, 2026 · Apple M4
Global Score
83 vs 69
Hardware Fit
58 vs 100
Quality Score
94 vs 56
Hardware
gemma-4-26b-a4b-it… qwen2.5-1.5b-instr…
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
gemma-4-26b-a4b-it… qwen2.5-1.5b-instr…
Tokens/sec10.358.1
First chunk8 ms211 ms
TTFT3.5 s211 ms
Load time10.9 sN/A
Memory usage6.4 GB1.5 GB
Memory %41%5%
HW Fit Score Breakdown
gemma-4-26b-a4b-it@iq3_…
Speed
19/50
TTFT
12/20
Memory
27/30
qwen2.5-1.5b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma-4-26b-a4b-it@iq3_…
Reasoning
18/20
Coding
19/20
Instruction
19/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen2.5-1.5b-instruct
Reasoning
9/20
Coding
10/20
Instruction
10/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate 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