Back to leaderboard

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

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

Global Score
20 vs 86
Hardware Fit
37 vs 78
Quality Score
12 vs 89

Hardware

qwen3.5:27b Kimi-48B:48B
MachineAZW GTR ProGMKtec NucBox EVO-T2S
CPUAMD RYZEN AI MAX+ 395Intel Core™ Ultra X7 358H
Cores3216
RAM125 GB64 GB
GPUAMD Radeon 8060SIntel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.5:27b Kimi-48B:48B
Tokens/sec10.622.8
First chunk358 ms721 ms
TTFT13.7 s721 ms
Load time10.8 s23.0 s
Memory usage39.7 GB25.5 GB
Memory %32%40%

HW Fit Score Breakdown

qwen3.5:27b

Speed
9/50
TTFT
0/20
Memory
28/30

Kimi-48B:48B

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

Quality

qwen3.5:27b

Reasoning
2/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor 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
View qwen3.5:27b details | View Kimi-48B:48B details

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