Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ i7-14700F

qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
85 vs 80
Hardware Fit
83 vs 62
Quality Score
86 vs 88

Hardware

Kimi-48B:48B qwen3.5-35b-a3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCDocker Container
CPUIntel Core™ i7-14700FIntel Gen Intel® Core™ i9-11900H
Cores2816
RAM64 GB15 GB
GPUNVIDIA GeForce RTX 5080TigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

Kimi-48B:48B qwen3.5-35b-a3b
Tokens/sec32.810.6
First chunk724 ms52 ms
TTFT724 ms3.2 s
Load time20.9 s7.6 s
Memory usage25.8 GB1.1 GB
Memory %41%7%

HW Fit Score Breakdown

Kimi-48B:48B

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

qwen3.5-35b-a3b

Speed
19/50
TTFT
13/20
Memory
30/30

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

qwen3.5-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
10/10
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