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 )

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

Global Score
90 vs 89
Hardware Fit
96 vs 95
Quality Score
88 vs 87

Hardware

Kimi-48B:48B qwen/qwen3-8b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMac mini
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M4 Pro
Cores2014
RAM55 GB64 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.28000macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

Kimi-48B:48B qwen/qwen3-8b
Tokens/sec62.733.4
First chunk397 ms257 ms
TTFT397 ms257 ms
Load time16.8 sN/A
Memory usage25.5 GB4.3 GB
Memory %47%7%

HW Fit Score Breakdown

Kimi-48B:48B

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

qwen/qwen3-8b

Speed
45/50
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

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View Kimi-48B:48B details | View qwen/qwen3-8b 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