qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
deepseek-coder-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
89 vs 82
Hardware Fit
97 vs 100
Quality Score
86 vs 74
Hardware
qwen/qwen3.6-35b-a3b deepseek-coder-v2:…
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M5 MaxCortex-X925
Cores1820
RAM64 GB122 GB
GPUApple M5 MaxDevice 2e12
OSmacOS 27.0Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen/qwen3.6-35b-a3b deepseek-coder-v2:…
Tokens/sec130.2117.2
First chunk5 ms275 ms
TTFT135 ms275 ms
Load timeN/A8.9 s
Memory usage26.6 GB17.9 GB
Memory %42%15%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
deepseek-coder-v2:16b
Speed
50/50
TTFT
20/20
Memory
30/30
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
deepseek-coder-v2:16b
Reasoning
8/20
Coding
19/20
Instruction
13/20
Structured
12/15
Math
14/15
Multilingual
8/10
Reasoning: Weak Coding: Strong 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