qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
yi:6b
OLLAMA GGUFllama · 6B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
77 vs 77
Hardware Fit
53 vs 100
Quality Score
87 vs 67
Hardware
qwen3.5:35b yi:6b
MachineASUSMacBook Air
CPUIntel Core™ i5-14600KFApple M4
Cores2010
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M4
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5:35b yi:6b
Tokens/sec16.027.6
First chunk719 msN/A
TTFT719 ms210 ms
Load time17.8 s0.4 s
Memory usage25.0 GB3.6 GB
Memory %79%11%
HW Fit Score Breakdown
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
yi:6b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5:35b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
yi:6b
Reasoning
11/20
Coding
12/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
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