solar:10.7b

llama · 11B · Q4_0

Good

Mar 2, 2026 · Apple M4

neural-chat:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

63 vs 67

Hardware Fit

87 vs 96

Quality Score

52 vs 55

Hardware

solar:10.7b 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

solar:10.7b neural-chat:7b

Tokens/sec15.822.5

TTFT353 ms242 ms

Load time0.4 s0.4 s

Memory usage6.6 GB4.5 GB

Memory %21%14%

HW Fit Score Breakdown

solar:10.7b

Speed

27/40

TTFT

30/30

Memory

30/30

neural-chat:7b

Speed

36/40

TTFT

30/30

Memory

30/30

Quality

solar:10.7b

Reasoning

8/20

Coding

8/20

Instruction

11/20

Structured

14/15

Math

4/15

Multilingual

7/10

Reasoning: Weak Coding: Weak 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 solar:10.7b details | View neural-chat:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running