Back to leaderboard

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

qwen2.5-coder-3b-instruct-mlx

LM-STUDIO MLX

qwen2 · 3B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score
88 vs 73
Hardware Fit
80 vs 100
Quality Score
92 vs 61

Hardware

gemma4:26b qwen2.5-coder-3b-i…
MachineASUSTeK COMPUTER INC. GX10MacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

gemma4:26b qwen2.5-coder-3b-i…
Tokens/sec66.752.3
First chunk583 ms285 ms
TTFT30.0 s285 ms
Load time6.7 sN/A
Memory usage17.6 GB1.6 GB
Memory %15%5%

HW Fit Score Breakdown

gemma4:26b

Speed
50/50
TTFT
0/20
Memory
30/30

qwen2.5-coder-3b-instru…

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

Quality

gemma4:26b

Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-coder-3b-instru…

Reasoning
7/20
Coding
14/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View gemma4:26b details | View qwen2.5-coder-3b-i… 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