Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
81 vs 75
Hardware Fit
68 vs 50
Quality Score
87 vs 86

Hardware

qwen/qwen3.8-27b qwen2.5:72b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 MaxCortex-X925
Cores1620
RAM128 GB122 GB
GPUApple M4 MaxDevice 2e12
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen/qwen3.8-27b qwen2.5:72b
Tokens/sec16.44.4
First chunk5 ms529 ms
TTFT742 ms529 ms
Load timeN/A49.7 s
Memory usage38.5 GB54.0 GB
Memory %30%44%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
18/50
TTFT
20/20
Memory
30/30

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

Quality

qwen/qwen3.8-27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5:72b

Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.8-27b details | View qwen2.5:72b 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