qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
62 vs 68
Hardware Fit
100 vs 59
Quality Score
46 vs 72
Hardware
qwen3.5:0.8b qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M1 MaxIntel Gen Intel® Core™ i7-13700K
Cores1024
RAM32 GB64 GB
GPUApple M1 MaxNVIDIA GeForce RTX 3070
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
qwen3.5:0.8b qwen2.5-coder:7b
Tokens/sec67.634.4
First chunk209 ms1991 ms
TTFT209 ms2.0 s
Load time1.9 s40.6 s
Memory usage2.6 GB5.0 GB
Memory %8%8%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
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
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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