Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
85 vs 81
Hardware Fit
95 vs 64
Quality Score
81 vs 88

Hardware

gemma4:e4b-mlx qwen3.8-27b-uncens…
MachineMacBook ProSystem manufacturer
CPUApple M2 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M2 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.5Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

gemma4:e4b-mlx qwen3.8-27b-uncens…
Tokens/sec47.311.7
First chunk258 ms50 ms
TTFT258 ms1.1 s
Load time5.1 sN/A
Memory usage7.9 GB15.8 GB
Memory %49%51%

HW Fit Score Breakdown

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
25/30

qwen3.8-27b-uncensored-…

Speed
19/50
TTFT
20/20
Memory
25/30

Quality

gemma4:e4b-mlx

Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.8-27b-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma4:e4b-mlx details | View qwen3.8-27b-uncens… 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