Back to leaderboard

qwen/qwen3.6-35b-a3b:2

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

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

google/gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_0

Excellent

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

Global Score
73 vs 82
Hardware Fit
50 vs 56
Quality Score
83 vs 93

Hardware

qwen/qwen3.6-35b-a… google/gemma-4-26b…
MachineSystem manufacturerDocker Container
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Gen Intel® Core™ i9-11900H
Cores1616
RAM31 GB15 GB
GPUNavi 44 [Radeon RX 9060 XT]TigerLake-H GT1 [UHD Graphics]
OSUbuntu 26.04.1 LTSUbuntu 26.04 LTS
Archx64x64
Power Modelow-powerperformance

Performance

qwen/qwen3.6-35b-a… google/gemma-4-26b…
Tokens/sec10.512.0
First chunk4 ms86 ms
TTFT1.7 s2.8 s
Load timeN/A57.2 s
Memory usage21.4 GB9.1 GB
Memory %69%59%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b:2

Speed
16/50
TTFT
18/20
Memory
16/30

google/gemma-4-26b-a4b-…

Speed
22/50
TTFT
14/20
Memory
20/30

Quality

qwen/qwen3.6-35b-a3b:2

Reasoning
16/20
Coding
15/20
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-4-26b-a4b-…

Reasoning
17/20
Coding
19/20
Instruction
20/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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