qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
89 vs 68
Hardware Fit
97 vs 59
Quality Score
86 vs 72
Hardware
qwen/qwen3.6-35b-a3b qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M5 MaxIntel Gen Intel® Core™ i7-13700K
Cores1824
RAM64 GB64 GB
GPUApple M5 MaxNVIDIA GeForce RTX 3070
OSmacOS 27.0Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
qwen/qwen3.6-35b-a3b qwen2.5-coder:7b
Tokens/sec130.234.4
First chunk5 ms1991 ms
TTFT135 ms2.0 s
Load timeN/A40.6 s
Memory usage26.6 GB5.0 GB
Memory %42%8%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
qwen/qwen3.6-35b-a3b
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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