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

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
77 vs 78
Hardware Fit
55 vs 47
Quality Score
86 vs 92

Hardware

qwen3.6-35b-a3b-mtp gemma4:31b
MachineDocker ContainerAZW GTR Pro
CPUIntel Gen Intel® Core™ i9-11900HAMD RYZEN AI MAX+ 395
Cores1632
RAM15 GB125 GB
GPUTigerLake-H GT1 [UHD Graphics]Radeon 8060S
OSUbuntu 26.04 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.6-35b-a3b-mtp gemma4:31b
Tokens/sec9.29.8
First chunk38 ms873 ms
TTFT4.7 s873 ms
Load time46.7 s7.0 s
Memory usage0.0 GB68.3 GB
Memory %0%55%

HW Fit Score Breakdown

qwen3.6-35b-a3b-mtp

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

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

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

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.6-35b-a3b-mtp details | View gemma4:31b 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