qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3.6:35b-a3b-q8_0
OLLAMA GGUFqwen35moe · 36.0B · Q8_0
Jul 7, 2026 · Cortex-X925
Global Score
61 vs 80
Hardware Fit
85 vs 79
Quality Score
51 vs 81
Hardware
qwen3:0.6b qwen3.6:35b-a3b-q8_0
MachineLENOVO 20L7CTO1WWASUSTeK COMPUTER INC. GX10
CPUIntel Core™ i5-8350UCortex-X925
Cores820
RAM23 GB122 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Device 2e12
OSFedora Linux 43Ubuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance
Performance
qwen3:0.6b qwen3.6:35b-a3b-q8_0
Tokens/sec27.055.5
First chunk597 ms528 ms
TTFT8.7 s30.0 s
Load time1.8 s32.6 s
Memory usage0.9 GB41.0 GB
Memory %4%34%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
qwen3.6:35b-a3b-q8_0
Speed
50/50
TTFT
0/20
Memory
29/30
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-q8_0
Reasoning
18/20
Coding
13/20
Instruction
17/20
Structured
10/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Adequate 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