Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

yi:6b

OLLAMA GGUF

llama · 6B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
80 vs 77
Hardware Fit
52 vs 100
Quality Score
92 vs 67

Hardware

qwen/qwen3.8-27b yi:6b
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 yi:6b
Tokens/sec16.127.6
First chunk14 msN/A
TTFT5.8 s210 ms
Load time8.5 s0.4 s
Memory usage0.0 GB3.6 GB
Memory %0%11%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
17/50
TTFT
5/20
Memory
30/30

yi:6b

Speed
40/50
TTFT
30/20
Memory
30/30

Quality

qwen/qwen3.8-27b

Reasoning
19/20
Coding
16/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

yi:6b

Reasoning
11/20
Coding
12/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
View qwen/qwen3.8-27b details | View yi:6b 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