qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.6:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
May 25, 2026 · Apple M4 Pro
Global Score
61 vs 70
Hardware Fit
85 vs 66
Quality Score
51 vs 71
Hardware
qwen3:0.6b qwen3.6:35b
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M4 Pro
Cores814
RAM23 GB48 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4 Pro
OSFedora Linux 43macOS 26.4.1
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3:0.6b qwen3.6:35b
Tokens/sec27.030.6
First chunk597 ms304 ms
TTFT8.7 s30.0 s
Load time1.8 s10.0 s
Memory usage0.9 GB28.1 GB
Memory %4%59%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
qwen3.6:35b
Speed
45/50
TTFT
0/20
Memory
21/30
Quality
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
qwen3.6:35b
Reasoning
18/20
Coding
12/20
Instruction
12/20
Structured
6/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Weak 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