Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
88 vs 68
Hardware Fit
90 vs 93
Quality Score
87 vs 57

Hardware

qwen/qwen3.6-35b-a3b google/gemma-4-e4b
MachineGMKtec EVO-X3LENOVO 82JQ
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 5800H
Cores3216
RAM120 GB16 GB
GPUAMD Radeon(TM) 8060S GraphicsNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b google/gemma-4-e4b
Tokens/sec49.026.2
First chunk44 ms17 ms
TTFT334 ms572 ms
Load time61.3 sN/A
Memory usage59.8 GB6.5 GB
Memory %50%41%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
45/50
TTFT
20/20
Memory
25/30

google/gemma-4-e4b

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

Quality

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
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

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
View qwen/qwen3.6-35b-a3b details | View google/gemma-4-e4b 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