Back to leaderboard

smollm2:1.7b

llama · 1.7B · Q8_0

Good

Mar 1, 2026 · Apple M4

neural-chat:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
63 vs 71
Hardware Fit
99 vs 96
Quality Score
39 vs 55

Hardware

smollm2:1.7b neural-chat:7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

smollm2:1.7b neural-chat:7b
Tokens/sec50.322.5
TTFT81 ms242 ms
Load time0.4 s0.4 s
Memory usage3.7 GB4.5 GB
Memory %12%14%

HW Fit Score Breakdown

smollm2:1.7b

Speed
40/40
TTFT
30/30
Memory
29/30

neural-chat:7b

Speed
36/40
TTFT
30/30
Memory
30/30

Quality

smollm2:1.7b

Reasoning
7/20
Coding
0/20
Instruction
12/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

neural-chat:7b

Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View smollm2:1.7b details | View neural-chat:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running