Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
62 vs 72
Hardware Fit
77 vs 35
Quality Score
55 vs 88

Hardware

google/gemma-4-e4b qwen/qwen3.5-35b-a3b
MachineLENOVO 82JQSystem manufacturer
CPUAMD Ryzen 7 5800HAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM16 GB32 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUAMD Radeon RX 9060 XT
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen/qwen3.5-35b-a3b
Tokens/sec27.68.3
First chunk23 ms32 ms
TTFT480 ms2.0 s
Load timeN/AN/A
Memory usage13.2 GB28.9 GB
Memory %83%91%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

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

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
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 qwen/qwen3.5-35b-a3b 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