Back to leaderboard

gemma-4-26b-a4b-it@iq3_xxs

LM-STUDIO GGUF

gemma4 · 26B · IQ3_XXS

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
83 vs 59
Hardware Fit
58 vs 63
Quality Score
94 vs 58

Hardware

gemma-4-26b-a4b-it… qwen3.8-27b-mlx
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M5 Max
Cores1618
RAM15 GB64 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M5 Max
OSUbuntu 26.04 LTSmacOS 27.0
Archx64arm64
Power Modeperformancebalanced

Performance

gemma-4-26b-a4b-it… qwen3.8-27b-mlx
Tokens/sec10.318.3
First chunk8 ms4 ms
TTFT3.5 s530 ms
Load time10.9 sN/A
Memory usage6.4 GB38.5 GB
Memory %41%60%

HW Fit Score Breakdown

gemma-4-26b-a4b-it@iq3_…

Speed
19/50
TTFT
12/20
Memory
27/30

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest