Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ i7-14700F

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 22, 2026 · Apple M1 Pro

Global Score
85 vs 69
Hardware Fit
83 vs 85
Quality Score
86 vs 62

Hardware

Kimi-48B:48B qwen3.5:4b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M1 Pro
Cores2810
RAM64 GB16 GB
GPUNVIDIA GeForce RTX 5080Apple M1 Pro
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

Kimi-48B:48B qwen3.5:4b
Tokens/sec32.836.9
First chunk724 ms474 ms
TTFT724 ms6.9 s
Load time20.9 s2.9 s
Memory usage25.8 GB5.3 GB
Memory %41%33%

HW Fit Score Breakdown

Kimi-48B:48B

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

qwen3.5:4b

Speed
50/50
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

Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate 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