Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 24, 2026 · Intel Core™ Ultra X7 358H

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
86 vs 66
Hardware Fit
78 vs 91
Quality Score
89 vs 55

Hardware

Kimi-48B:48B qwen3.8-27b-mlx
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M5 Max
Cores1618
RAM64 GB64 GB
GPUIntel(R) Arc(TM) B390 GPUApple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

Kimi-48B:48B qwen3.8-27b-mlx
Tokens/sec23.133.2
First chunk752 ms7 ms
TTFT752 ms311 ms
Load time22.2 sN/A
Memory usage25.5 GB0.5 GB
Memory %40%1%

HW Fit Score Breakdown

Kimi-48B:48B

Speed
31/50
TTFT
20/20
Memory
27/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
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

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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