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-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Aug 22, 2026 · Intel Xeon® E5-2637 v3

Global Score
62 vs 82
Hardware Fit
77 vs 69
Quality Score
55 vs 87

Hardware

google/gemma-4-e4b qwen3.5:35b-a3b-q4…
MachineLENOVO 82JQDell Inc. Precision Tower 7910
CPUAMD Ryzen 7 5800HIntel Xeon® E5-2637 v3
Cores1616
RAM16 GB96 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3.5:35b-a3b-q4…
Tokens/sec27.620.4
First chunk23 ms1362 ms
TTFT480 ms1.4 s
Load timeN/A34.2 s
Memory usage13.2 GB22.7 GB
Memory %83%24%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen3.5:35b-a3b-q4_K_M

Speed
23/50
TTFT
16/20
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-q4_K_M

Reasoning
17/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View google/gemma-4-e4b details | View qwen3.5:35b-a3b-q4… 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