solar:10.7b
OLLAMA GGUFllama · 11B · Q4_0
Mar 2, 2026 · Apple M4
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
63 vs 73
Hardware Fit
87 vs 100
Quality Score
52 vs 62
Hardware
solar:10.7b qwen3:0.6b
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 qwen3:0.6b
Tokens/sec15.8145.2
First chunkN/AN/A
TTFT353 ms1.4 s
Load time0.4 s0.7 s
Memory usage6.6 GB4.1 GB
Memory %21%13%
HW Fit Score Breakdown
solar:10.7b
Speed
27/50
TTFT
30/20
Memory
30/30
qwen3:0.6b
Speed
40/50
TTFT
30/20
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
qwen3:0.6b
Reasoning
14/20
Coding
3/20
Instruction
11/20
Structured
13/15
Math
13/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest