Back to leaderboard

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

Global Score
88 vs 62
Hardware Fit
77 vs 100
Quality Score
93 vs 46

Hardware

gemma-4-26b-a4b-it… qwen3.5:0.8b
MachineASUSMacBook Pro
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M1 Max
Cores1610
RAM31 GB32 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M1 Max
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

gemma-4-26b-a4b-it… qwen3.5:0.8b
Tokens/sec169.665.8
First chunk9 ms230 ms
TTFT108 ms230 ms
Load timeN/A1.5 s
Memory usage26.0 GB2.6 GB
Memory %85%8%

HW Fit Score Breakdown

gemma-4-26b-a4b-it-qat

Speed
50/50
TTFT
20/20
Memory
7/30

qwen3.5:0.8b

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

Quality

gemma-4-26b-a4b-it-qat

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View gemma-4-26b-a4b-it… details | View qwen3.5:0.8b details

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