Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
gemma-4-31b-it-mlx
LM-STUDIO MLXgemma4 · 31B · 8bit
Aug 19, 2026 · Apple M4 Max
Global Score
85 vs 85
Hardware Fit
83 vs 64
Quality Score
86 vs 94
Hardware
Kimi-48B:48B gemma-4-31b-it-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M4 Max
Cores2816
RAM64 GB128 GB
GPUNVIDIA GeForce RTX 5080Apple M4 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B gemma-4-31b-it-mlx
Tokens/sec32.813.6
First chunk724 ms16 ms
TTFT724 ms558 ms
Load time20.9 s12.3 s
Memory usage25.8 GB0.0 GB
Memory %41%0%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
gemma-4-31b-it-mlx
Speed
14/50
TTFT
20/20
Memory
30/30
Quality
Kimi-48B:48B
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
13/15
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