Back to leaderboard

deepscaler:1.5b

OLLAMA GGUF

qwen2 · 1.8B · F16

Good

Oct 11, 2026 · AMD Ryzen 5 5500

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

Global Score
64 vs 88
Hardware Fit
98 vs 77
Quality Score
49 vs 93

Hardware

deepscaler:1.5b gemma-4-26b-a4b-it…
MachineMicrosoft WSLASUS
CPUAMD Ryzen 5 5500AMD Ryzen 7 7800X3D 8-Core Processor
Cores1216
RAM8 GB31 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 26.04.1 LTScachyos rolling
Archx64x64
Power Modeunknownperformance

Performance

deepscaler:1.5b gemma-4-26b-a4b-it…
Tokens/sec104.6169.2
First chunk849 ms5 ms
TTFT850 ms122 ms
Load time10.5 sN/A
Memory usage3.0 GB26.0 GB
Memory %40%85%

HW Fit Score Breakdown

deepscaler:1.5b

Speed
50/50
TTFT
20/20
Memory
28/30

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

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

Quality

deepscaler:1.5b

Reasoning
10/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
11/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Weak

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
View deepscaler:1.5b details | View gemma-4-26b-a4b-it… 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