Back to leaderboard

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Excellent

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

falcon3-1b-instruct

LM-STUDIO MLX

llama · 1B · 3bit

Marginal

Mar 4, 2026 · Apple M4

Global Score
89 vs 54
Hardware Fit
95 vs 100
Quality Score
87 vs 34

Hardware

gemma4:26b falcon3-1b-instruct
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

gemma4:26b falcon3-1b-instruct
Tokens/sec48.3121.8
First chunk346 ms176 ms
TTFT346 ms176 ms
Load time4.4 sN/A
Memory usage36.1 GB0.7 GB
Memory %29%2%

HW Fit Score Breakdown

gemma4:26b

Speed
45/50
TTFT
20/20
Memory
30/30

falcon3-1b-instruct

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

Quality

gemma4:26b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
14/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

falcon3-1b-instruct

Reasoning
7/20
Coding
1/20
Instruction
12/20
Structured
7/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Weak
View gemma4:26b details | View falcon3-1b-instruct 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