Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
68 vs 88
Hardware Fit
93 vs 85
Quality Score
57 vs 89

Hardware

google/gemma-4-e4b huihui-qwen3.6-35b…
MachineLENOVO 82JQGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD Ryzen 7 5800HAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM16 GB47 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

google/gemma-4-e4b huihui-qwen3.6-35b…
Tokens/sec26.237.7
First chunk17 ms18 ms
TTFT572 ms2.9 s
Load timeN/AN/A
Memory usage6.5 GB26.1 GB
Memory %41%56%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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