Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
gemma-4-31b-it-mlx
LM-STUDIO MLXgemma4 · 31B · 8bit
Aug 19, 2026 · Apple M4 Max
Global Score
85 vs 85
Hardware Fit
78 vs 64
Quality Score
88 vs 94
Hardware
Kimi-48B:48B gemma-4-31b-it-mlx
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxMacBook Pro
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorApple M4 Max
Cores3216
RAM31 GB128 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUApple M4 Max
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B gemma-4-31b-it-mlx
Tokens/sec43.013.6
First chunk700 ms16 ms
TTFT700 ms558 ms
Load time29.4 s12.3 s
Memory usage25.8 GB0.0 GB
Memory %83%0%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
8/30
gemma-4-31b-it-mlx
Speed
14/50
TTFT
20/20
Memory
30/30
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
gemma-4-31b-it-mlx
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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