Back to leaderboard

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
72 vs 68
Hardware Fit
35 vs 93
Quality Score
88 vs 57

Hardware

qwen/qwen3.5-35b-a3b google/gemma-4-e4b
MachineSystem manufacturerLENOVO 82JQ
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 7 5800H
Cores1616
RAM32 GB16 GB
GPUAMD Radeon RX 9060 XTNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b google/gemma-4-e4b
Tokens/sec8.326.2
First chunk32 ms17 ms
TTFT2.0 s572 ms
Load timeN/AN/A
Memory usage28.9 GB6.5 GB
Memory %91%41%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

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

google/gemma-4-e4b

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

Quality

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

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/qwen3.5-35b-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