Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Apr 28, 2026 · Intel Xeon® Gold 6230

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ Ultra X7 358H

Global Score
80 vs 86
Hardware Fit
85 vs 78
Quality Score
78 vs 89

Hardware

qwen3:8b Kimi-48B:48B
MachineHP HP Z8 G4 WorkstationGMKtec NucBox EVO-T2S
CPUIntel Xeon® Gold 6230Intel Core™ Ultra X7 358H
Cores8016
RAM252 GB64 GB
GPUTU104GL [Quadro RTX 5000]Intel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3:8b Kimi-48B:48B
Tokens/sec65.122.8
First chunk289 ms721 ms
TTFT4.2 s721 ms
Load time4.6 s23.0 s
Memory usage5.6 GB25.5 GB
Memory %2%40%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
5/20
Memory
30/30

Kimi-48B:48B

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

Quality

qwen3:8b

Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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