deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
64 vs 84
Hardware Fit
98 vs 69
Quality Score
49 vs 91
Hardware
deepscaler:1.5b gptoss · 20.9B · M…
MachineMicrosoft WSLMac Pro
CPUAMD Ryzen 5 5500Intel Core™ i5-10400
Cores1212
RAM8 GB32 GB
GPUIntegrated / UnknownAMD Radeon RX 6700 XT
OSUbuntu 26.04.1 LTSmacOS 26.5.1
Archx64x64
Power Modeunknownbalanced
Performance
deepscaler:1.5b gptoss · 20.9B · M…
Tokens/sec104.617.5
First chunk849 ms643 ms
TTFT850 ms7.7 s
Load time10.5 s0.0 s
Memory usage3.0 GB0.8 GB
Memory %40%3%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
Memory
30/30
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest