hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0
OLLAMA GGUFllama · 3.93B · unknown
Aug 22, 2026 · Apple M1 Pro
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
52 vs 89
Hardware Fit
75 vs 95
Quality Score
42 vs 87
Hardware
hf.co/Edge-Quant/N… gemma4:26b
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
hf.co/Edge-Quant/N… gemma4:26b
Tokens/sec43.548.3
First chunk225 ms346 ms
TTFT30.0 s346 ms
Load time2.7 s4.4 s
Memory usage8.2 GB36.1 GB
Memory %51%29%
HW Fit Score Breakdown
hf.co/Edge-Quant/Nanbei…
Speed
50/50
TTFT
0/20
Memory
25/30
gemma4:26b
Speed
45/50
TTFT
20/20
Memory
30/30
Quality
hf.co/Edge-Quant/Nanbei…
Reasoning
13/20
Coding
1/20
Instruction
7/20
Structured
1/15
Math
13/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate
gemma4:26b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
14/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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