Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
Feb 28, 2026 · Apple M4 Pro
Global Score
86 vs 73
Hardware Fit
78 vs 100
Quality Score
89 vs 61
Hardware
Kimi-48B:48B llama3.2:latest
MachineGMKtec NucBox EVO-T2SMac Mini
CPUIntel Core™ Ultra X7 358HApple M4 Pro
Cores1614
RAM64 GB64 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedunknown
Performance
Kimi-48B:48B llama3.2:latest
Tokens/sec23.198.9
First chunk752 msN/A
TTFT752 ms125 ms
Load time22.2 s2.3 s
Memory usage25.5 GB22.1 GB
Memory %40%35%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
llama3.2:latest
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3.2:latest
Reasoning
11/20
Coding
14/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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