Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score
94 vs 90
Hardware Fit
91 vs 96
Quality Score
95 vs 88

Hardware

gpt-oss:20b Kimi-48B:48B
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUAMD RYZEN AI MAX+ 395NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores3220
RAM64 GB55 GB
GPUAMD Radeon(TM) 8060S GraphicsNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced

Performance

gpt-oss:20b Kimi-48B:48B
Tokens/sec48.062.7
First chunk357 ms397 ms
TTFT2.3 s397 ms
Load time0.2 s16.8 s
Memory usage16.4 GB25.5 GB
Memory %26%47%

HW Fit Score Breakdown

gpt-oss:20b

Speed
50/50
TTFT
11/20
Memory
30/30

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
26/30

Quality

gpt-oss:20b

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

Kimi-48B:48B

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
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