Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

Apr 21, 2026 · Apple M2 Max

Global Score
62 vs 71
Hardware Fit
77 vs 92
Quality Score
55 vs 62

Hardware

google/gemma-4-e4b qwen3.5-35b-a3b-un…
MachineLENOVO 82JQMac Studio
CPUAMD Ryzen 7 5800HApple M2 Max
Cores1612
RAM16 GB96 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUApple M2 Max
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3.5-35b-a3b-un…
Tokens/sec27.659.8
First chunk23 ms5 ms
TTFT480 ms2.4 s
Load timeN/A8.5 s
Memory usage13.2 GB0.4 GB
Memory %83%0%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen3.5-35b-a3b-uncenso…

Speed
50/50
TTFT
12/20
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

qwen3.5-35b-a3b-uncenso…

Reasoning
18/20
Coding
8/20
Instruction
13/20
Structured
6/15
Math
12/15
Multilingual
5/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Adequate

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