Back to leaderboard

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

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
88 vs 82
Hardware Fit
77 vs 81
Quality Score
93 vs 82

Hardware

gemma-4-26b-a4b-it… qwen3.5:9b
MachineASUSAZW GTR Pro
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1632
RAM31 GB125 GB
GPUNVIDIA GeForce RTX 4090, RaphaelIntegrated / Apple Silicon
OScachyos rollingUbuntu 24.04.4 LTS
Archx64x64
Power Modeperformanceperformance

Performance

gemma-4-26b-a4b-it… qwen3.5:9b
Tokens/sec169.230.8
First chunk5 ms195 ms
TTFT122 ms195 ms
Load timeN/A6.8 s
Memory usage26.0 GB18.8 GB
Memory %85%15%

HW Fit Score Breakdown

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

Speed
50/50
TTFT
20/20
Memory
7/30

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

Quality

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

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma-4-26b-a4b-it… details | View qwen3.5:9b 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