Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
62 vs 66
Hardware Fit
77 vs 87
Quality Score
55 vs 57

Hardware

google/gemma-4-e4b granite-3.3-2b-ins…
MachineLENOVO 82JQMacBook Air
CPUAMD Ryzen 7 5800HApple M4
Cores1610
RAM16 GB32 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUApple M4
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b granite-3.3-2b-ins…
Tokens/sec27.618.3
First chunk23 ms541 ms
TTFT480 ms541 ms
Load timeN/AN/A
Memory usage13.2 GB4.7 GB
Memory %83%15%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

granite-3.3-2b-instruct

Speed
37/50
TTFT
20/20
Memory
30/30

Quality

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

granite-3.3-2b-instruct

Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View google/gemma-4-e4b details | View granite-3.3-2b-ins… 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