Back to leaderboard

gemma4:26b

OLLAMA GGUF

gemma4 · 25.2B · Q4_K_M

Not Rec.

Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor

qwen3-coder-30b-a3b-instruct-mlx

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

Global Score
84 vs 87
Hardware Fit
80 vs 85
Quality Score
86 vs 88

Hardware

gemma4:26b qwen3-coder-30b-a3…
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M1 Pro
Cores3210
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 3090Apple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

gemma4:26b qwen3-coder-30b-a3…
Tokens/sec147.645.7
First chunk139 ms17 ms
TTFT30.0 s390 ms
Load time21.3 sN/A
Memory usage1.7 GB22.4 GB
Memory %5%70%

HW Fit Score Breakdown

gemma4:26b

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

qwen3-coder-30b-a3b-ins…

Speed
50/50
TTFT
20/20
Memory
15/30

Quality

gemma4:26b

Reasoning
17/20
Coding
14/20
Instruction
18/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-coder-30b-a3b-ins…

Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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