Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 19, 2026 · Apple M4 Max

nous-hermes2:latest

OLLAMA GGUF

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
83 vs 68
Hardware Fit
68 vs 87
Quality Score
90 vs 60

Hardware

qwen/qwen3.8-27b nous-hermes2: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 nous-hermes2:latest
Tokens/sec27.615.9
First chunk10 msN/A
TTFT4.6 s345 ms
Load timeN/A0.4 s
Memory usage21.0 GB6.6 GB
Memory %16%21%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
32/50
TTFT
6/20
Memory
30/30

nous-hermes2:latest

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

Quality

qwen/qwen3.8-27b

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

nous-hermes2:latest

Reasoning
11/20
Coding
9/20
Instruction
12/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen/qwen3.8-27b details | View nous-hermes2: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