Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

qwen/qwen3.6-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Oct 22, 2026 · Apple M1 Pro

Global Score
84 vs 80
Hardware Fit
66 vs 56
Quality Score
92 vs 90

Hardware

qwen3.8:27b qwen/qwen3.6-27b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.5 LTSmacOS 15.6.1
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen3.8:27b qwen/qwen3.6-27b
Tokens/sec29.410.8
First chunk306 ms16 ms
TTFT4.8 s2.6 s
Load time5.3 sN/A
Memory usage16.2 GB21.0 GB
Memory %13%66%

HW Fit Score Breakdown

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

qwen/qwen3.6-27b

Speed
23/50
TTFT
16/20
Memory
17/30

Quality

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen/qwen3.6-27b

Reasoning
18/20
Coding
18/20
Instruction
16/20
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