qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
microllm-250m:latest
OLLAMA GGUFllama · 256.74M · F16
Jul 5, 2026 · Apple M4 Pro
Global Score
77 vs 34
Hardware Fit
53 vs 100
Quality Score
87 vs 6
Hardware
qwen3.5:35b microllm-250m:latest
MachineASUSMac mini
CPUIntel Core™ i5-14600KFApple M4 Pro
Cores2012
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERApple M4 Pro
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5:35b microllm-250m:latest
Tokens/sec16.0291.6
First chunk719 ms50 ms
TTFT719 ms79 ms
Load time17.8 s0.0 s
Memory usage25.0 GB0.6 GB
Memory %79%2%
HW Fit Score Breakdown
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
microllm-250m:latest
Speed
50/50
TTFT
20/20
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
microllm-250m:latest
Reasoning
1/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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