Back to leaderboard

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
90 vs 65
Hardware Fit
96 vs 73
Quality Score
88 vs 62

Hardware

Kimi-48B:48B qwen3.5:4b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLAZW GTR Pro
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD RYZEN AI MAX+ 395
Cores2032
RAM55 GB125 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUAMD Radeon 8060S
OSMicrosoft Windows 11 Pro 10.0.28000Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

Kimi-48B:48B qwen3.5:4b
Tokens/sec62.745.7
First chunk397 ms180 ms
TTFT397 ms30.0 s
Load time16.8 s5.3 s
Memory usage25.5 GB16.2 GB
Memory %47%13%

HW Fit Score Breakdown

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
26/30

qwen3.5:4b

Speed
43/50
TTFT
0/20
Memory
30/30

Quality

Kimi-48B:48B

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:4b

Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
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