qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
Global Score
61 vs 62
Hardware Fit
85 vs 100
Quality Score
51 vs 46
Hardware
qwen3:0.6b qwen3.5:0.8b
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Max
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Max
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3:0.6b qwen3.5:0.8b
Tokens/sec27.067.6
First chunk597 ms209 ms
TTFT8.7 s209 ms
Load time1.8 s1.9 s
Memory usage0.9 GB2.6 GB
Memory %4%8%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
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
qwen3.5:0.8b
Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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