Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

Global Score
87 vs 80
Hardware Fit
83 vs 60
Quality Score
88 vs 88

Hardware

qwen/qwen3.8-27b qwen3-coder:30b
MachineMacBook ProASUS
CPUApple M4 MaxIntel Gen Intel® Core™ i7-12700K
Cores1620
RAM128 GB96 GB
GPUApple M4 MaxParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSmacOS 26.5.2Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b qwen3-coder:30b
Tokens/sec29.114.7
First chunk9 ms796 ms
TTFT650 ms796 ms
Load timeN/A0.2 s
Memory usage21.0 GB17.9 GB
Memory %16%19%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

qwen3-coder:30b

Speed
14/50
TTFT
19/20
Memory
27/30

Quality

qwen/qwen3.8-27b

Reasoning
18/20
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

qwen3-coder:30b

Reasoning
17/20
Coding
19/20
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
View qwen/qwen3.8-27b details | View qwen3-coder:30b 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