Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
google/gemma-3-27b
LM-STUDIO MLXgemma3 · 27B · 4bit
Mar 19, 2026 · Apple M4
Global Score
85 vs 71
Hardware Fit
78 vs 35
Quality Score
88 vs 86
Hardware
Kimi-48B:48B google/gemma-3-27b
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxMac mini
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorApple M4
Cores3210
RAM31 GB24 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUApple M4
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B google/gemma-3-27b
Tokens/sec43.05.9
First chunk700 ms19 ms
TTFT700 ms1.8 s
Load time29.4 sN/A
Memory usage25.8 GB22.0 GB
Memory %83%92%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
8/30
google/gemma-3-27b
Speed
12/50
TTFT
19/20
Memory
4/30
Quality
Kimi-48B:48B
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
google/gemma-3-27b
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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