qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.6:35b-a3b-coding-nvfp4
OLLAMA GGUFnvfp4
May 25, 2026 · Apple M4 Pro
Global Score
61 vs 76
Hardware Fit
85 vs 77
Quality Score
51 vs 76
Hardware
qwen3:0.6b qwen3.6:35b-a3b-co…
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-a3b-co…
Tokens/sec27.072.7
First chunk597 ms147 ms
TTFT8.7 s30.0 s
Load time1.8 s5.7 s
Memory usage0.9 GB19.6 GB
Memory %4%41%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
qwen3.6:35b-a3b-coding-…
Speed
50/50
TTFT
0/20
Memory
27/30
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-a3b-coding-…
Reasoning
19/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Weak 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