Back to leaderboard

qwen3.5:27b

qwen35 · 27.8B · Q4_K_M

Good

Mar 3, 2026 · Apple M4

nous-hermes2:latest

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
75 vs 68
Hardware Fit
67 vs 87
Quality Score
79 vs 60

Hardware

qwen3.5:27b nous-hermes2:latest
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:27b nous-hermes2:latest
Tokens/sec4.415.9
TTFT1.1 s345 ms
Load time13.2 s0.4 s
Memory usage22.7 GB6.6 GB
Memory %71%21%

HW Fit Score Breakdown

qwen3.5:27b

Speed
7/40
TTFT
30/30
Memory
30/30

nous-hermes2:latest

Speed
27/40
TTFT
30/30
Memory
30/30

Quality

qwen3.5:27b

Reasoning
16/20
Coding
17/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak 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 qwen3.5:27b details | View nous-hermes2:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running