Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Oct 31, 2026 · AMD RYZEN AI MAX+ 395

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

Global Score
81 vs 77
Hardware Fit
84 vs 67
Quality Score
79 vs 81

Hardware

google/gemma-4-e4b qwen3.5-9b-mlx
MachineGMKtec EVO-X3Mac mini
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3214
RAM120 GB64 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3.5-9b-mlx
Tokens/sec47.320.3
First chunk23 ms4216 ms
TTFT1.9 s4.2 s
Load timeN/AN/A
Memory usage13.2 GB5.6 GB
Memory %11%9%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
44/50
TTFT
10/20
Memory
30/30

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

Quality

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View google/gemma-4-e4b details | View qwen3.5-9b-mlx 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