Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
86 vs 62
Hardware Fit
78 vs 77
Quality Score
89 vs 55

Hardware

Kimi-48B:48B google/gemma-4-e4b
MachineGMKtec NucBox EVO-T2SLENOVO 82JQ
CPUIntel Core™ Ultra X7 358HAMD Ryzen 7 5800H
Cores1616
RAM64 GB16 GB
GPUIntel(R) Arc(TM) B390 GPUNVIDIA GeForce RTX 3060 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

Kimi-48B:48B google/gemma-4-e4b
Tokens/sec23.127.6
First chunk752 ms23 ms
TTFT752 ms480 ms
Load time22.2 sN/A
Memory usage25.5 GB13.2 GB
Memory %40%83%

HW Fit Score Breakdown

Kimi-48B:48B

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

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

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

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View Kimi-48B:48B details | View google/gemma-4-e4b 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