qwen3.5:4b
OLLAMA GGUFqwen35 · 4.2B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
OLLAMA GGUFgemma4 · 7.52B · unknown
Aug 24, 2026 · Apple M1 Pro
Global Score
81 vs 87
Hardware Fit
98 vs 100
Quality Score
74 vs 82
Hardware
qwen3.5:4b hf.co/unsloth/gemm…
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M1 Pro
Cores1210
RAM8 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 26.6.2
Archx64arm64
Power Modeunknownbalanced
Performance
qwen3.5:4b hf.co/unsloth/gemm…
Tokens/sec93.735.0
First chunk249 ms204 ms
TTFT249 ms204 ms
Load time10.1 s3.9 s
Memory usage2.9 GB4.9 GB
Memory %38%31%
HW Fit Score Breakdown
qwen3.5:4b
Speed
50/50
TTFT
20/20
Memory
28/30
hf.co/unsloth/gemma-4-E…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:4b
Reasoning
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
hf.co/unsloth/gemma-4-E…
Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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