Back to leaderboard

nous-hermes2:latest

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

qwen3:1.7b

qwen3 · 2.0B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score
71 vs 70
Hardware Fit
87 vs 87
Quality Score
60 vs 59

Hardware

nous-hermes2:latest qwen3:1.7b
MachineMacBook Air—
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

nous-hermes2:latest qwen3:1.7b
Tokens/sec15.937.9
TTFT345 ms3.1 s
Load time0.4 s1.2 s
Memory usage6.6 GB4.9 GB
Memory %21%15%

HW Fit Score Breakdown

nous-hermes2:latest

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

qwen3:1.7b

Speed
40/40
TTFT
17/30
Memory
30/30

Quality

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

qwen3:1.7b

Reasoning
16/20
Coding
0/20
Instruction
13/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View nous-hermes2:latest details | View qwen3:1.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running