qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
Global Score
64 vs 66
Hardware Fit
69 vs 100
Quality Score
62 vs 52
Hardware
qwen3.5:4b hf.co/empero-ai/Qw…
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M1 Pro
Cores810
RAM15 GB16 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M1 Pro
OSPop 24.04 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
qwen3.5:4b hf.co/empero-ai/Qw…
Tokens/sec7.440.2
First chunk1815 ms325 ms
TTFT1.8 s325 ms
Load time10.9 s3.1 s
Memory usage3.5 GB4.7 GB
Memory %23%30%
HW Fit Score Breakdown
qwen3.5:4b
Speed
19/50
TTFT
20/20
Memory
30/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:4b
Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
hf.co/empero-ai/Qwen3.8…
Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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