Back to leaderboard

qwen3.6-35b-a3b-mtp

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
77 vs 62
Hardware Fit
55 vs 77
Quality Score
86 vs 55

Hardware

qwen3.6-35b-a3b-mtp google/gemma-4-e4b
MachineDocker ContainerLENOVO 82JQ
CPUIntel Gen Intel® Core™ i9-11900HAMD Ryzen 7 5800H
Cores1616
RAM15 GB16 GB
GPUTigerLake-H GT1 [UHD Graphics]NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 26.04 LTSMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.6-35b-a3b-mtp google/gemma-4-e4b
Tokens/sec9.227.6
First chunk38 ms23 ms
TTFT4.7 s480 ms
Load time46.7 sN/A
Memory usage0.0 GB13.2 GB
Memory %0%83%

HW Fit Score Breakdown

qwen3.6-35b-a3b-mtp

Speed
16/50
TTFT
9/20
Memory
30/30

google/gemma-4-e4b

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

Quality

qwen3.6-35b-a3b-mtp

Reasoning
16/20
Coding
18/20
Instruction
15/20
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
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
View qwen3.6-35b-a3b-mtp 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