hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16
OLLAMA GGUFllama · 2.99B · BF16
Aug 22, 2026 · Apple M1 Pro
deepseek-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
65 vs 69
Hardware Fit
94 vs 100
Quality Score
52 vs 55
Hardware
hf.co/bartowski/ai… deepseek-v2:16b
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/bartowski/ai… deepseek-v2:16b
Tokens/sec29.656.6
First chunk264 msN/A
TTFT264 ms239 ms
Load time3.8 s1.2 s
Memory usage8.4 GB17.7 GB
Memory %53%55%
HW Fit Score Breakdown
hf.co/bartowski/ai9star…
Speed
50/50
TTFT
20/20
Memory
24/30
deepseek-v2:16b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
hf.co/bartowski/ai9star…
Reasoning
17/20
Coding
14/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
deepseek-v2:16b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
10/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate 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