Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

llama3:latest

OLLAMA GGUF

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
87 vs 71
Hardware Fit
83 vs 95
Quality Score
88 vs 60

Hardware

qwen/qwen3.8-27b llama3:latest
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM128 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b llama3:latest
Tokens/sec29.122.3
First chunk9 msN/A
TTFT650 ms295 ms
Load timeN/A0.8 s
Memory usage21.0 GB5.6 GB
Memory %16%18%

HW Fit Score Breakdown

qwen/qwen3.8-27b

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

llama3:latest

Speed
35/50
TTFT
30/20
Memory
30/30

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

llama3:latest

Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen/qwen3.8-27b details | View llama3:latest 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