Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

qwen2.5-7b-instruct

LM-STUDIO MLX

qwen2 · 7B · 4bit

Excellent

Mar 3, 2026 · Apple M4

Global Score
90 vs 84
Hardware Fit
96 vs 97
Quality Score
88 vs 78

Hardware

Kimi-48B:48B qwen2.5-7b-instruct
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMacBook Air
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M4
Cores2010
RAM55 GB32 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M4
OSMicrosoft Windows 11 Pro 10.0.28000macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

Kimi-48B:48B qwen2.5-7b-instruct
Tokens/sec62.724.4
First chunk397 ms464 ms
TTFT397 ms464 ms
Load time16.8 sN/A
Memory usage25.5 GB4.0 GB
Memory %47%13%

HW Fit Score Breakdown

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
26/30

qwen2.5-7b-instruct

Speed
47/50
TTFT
20/20
Memory
30/30

Quality

Kimi-48B:48B

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-7b-instruct

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View Kimi-48B:48B details | View qwen2.5-7b-instruct details

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