Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
Global Score
85 vs 59
Hardware Fit
83 vs 63
Quality Score
86 vs 58
Hardware
Kimi-48B:48B qwen3.8-27b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M5 Max
Cores2818
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 5080Apple M5 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B qwen3.8-27b-mlx
Tokens/sec32.818.3
First chunk724 ms4 ms
TTFT724 ms530 ms
Load time20.9 sN/A
Memory usage25.8 GB38.5 GB
Memory %41%60%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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