Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ i7-14700F

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

Hardware

qwen3.5:4b Kimi-48B:48B
MachineLENOVO 20U30029MBHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUIntel Core™ i5-10210UIntel Core™ i7-14700F
Cores828
RAM15 GB64 GB
GPUCometLake-U GT2 [UHD Graphics]NVIDIA GeForce RTX 5080
OSPop 24.04 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5:4b Kimi-48B:48B
Tokens/sec7.432.8
First chunk1815 ms724 ms
TTFT1.8 s724 ms
Load time10.9 s20.9 s
Memory usage3.5 GB25.8 GB
Memory %23%41%

HW Fit Score Breakdown

qwen3.5:4b

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

Kimi-48B:48B

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

Quality

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

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

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