qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
83 vs 78
Hardware Fit
99 vs 51
Quality Score
76 vs 89
Hardware
qwen3.5:4b qwen3-next:80b-a3b…
MachineMacBook ProDell Inc. Precision Tower 7910
CPUApple M1 ProIntel Xeon® E5-2637 v3
Cores1016
RAM16 GB96 GB
GPUApple M1 ProNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSmacOS 26.6.2Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5:4b qwen3-next:80b-a3b…
Tokens/sec36.68.7
First chunk204 ms1251 ms
TTFT204 ms1.3 s
Load time2.7 s61.6 s
Memory usage5.3 GB48.3 GB
Memory %33%50%
HW Fit Score Breakdown
qwen3.5:4b
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
17/20
Memory
25/30
Quality
qwen3.5:4b
Reasoning
16/20
Coding
14/20
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
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong 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