gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
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
85 vs 78
Hardware Fit
77 vs 51
Quality Score
89 vs 89
Hardware
gemma4:26b qwen3-next:80b-a3b…
MachineMac miniDell Inc. Precision Tower 7910
CPUApple M4Intel Xeon® E5-2637 v3
Cores1016
RAM24 GB96 GB
GPUApple M4NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSmacOS 26.3Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:26b qwen3-next:80b-a3b…
Tokens/sec24.58.7
First chunk1481 ms1251 ms
TTFT1.5 s1.3 s
Load time24.7 s61.6 s
Memory usage20.3 GB48.3 GB
Memory %85%50%
HW Fit Score Breakdown
gemma4:26b
Speed
49/50
TTFT
20/20
Memory
8/30
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
17/20
Memory
25/30
Quality
gemma4:26b
Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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