Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ i7-14700F

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
85 vs 62
Hardware Fit
83 vs 35
Quality Score
86 vs 73

Hardware

Kimi-48B:48B qwen3.5-4b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMac mini
CPUIntel Core™ i7-14700FApple M4 Pro
Cores2814
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 5080Apple M4 Pro
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

Kimi-48B:48B qwen3.5-4b-mlx
Tokens/sec32.80.0
First chunk724 ms5548 ms
TTFT724 ms5.5 s
Load time20.9 sN/A
Memory usage25.8 GB2.9 GB
Memory %41%5%

HW Fit Score Breakdown

Kimi-48B:48B

Speed
36/50
TTFT
20/20
Memory
27/30

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

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

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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