qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
Global Score
18 vs 97
Hardware Fit
53 vs 95
Quality Score
3 vs 98
Hardware
qwen3.5:0.8b qwen3-30b-a3b-thin…
MachineLENOVO 20L7CTO1WWMac Studio
CPUIntel Core™ i5-8350UApple M2 Max
Cores812
RAM23 GB96 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M2 Max
OSFedora Linux 43macOS 26.1
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:0.8b qwen3-30b-a3b-thin…
Tokens/sec9.479.6
First chunk799 ms11 ms
TTFT30.0 s1.7 s
Load time3.3 s7.1 s
Memory usage1.9 GB0.0 GB
Memory %8%0%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
23/50
TTFT
0/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
Quality
qwen3.5:0.8b
Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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