hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16
OLLAMA GGUFllama · 2.99B · BF16
Aug 22, 2026 · Apple M1 Pro
lmstudio-community/gemma-4-e4b-it
LM-STUDIO GGUFgemma4 · Q4_K_M
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
65 vs 76
Hardware Fit
94 vs 67
Quality Score
52 vs 80
Hardware
hf.co/bartowski/ai… lmstudio-community…
MachineMacBook ProDocker Container
CPUApple M1 ProIntel Gen Intel® Core™ i9-11900H
Cores1016
RAM16 GB15 GB
GPUApple M1 ProTigerLake-H GT1 [UHD Graphics]
OSmacOS 26.6.2Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
hf.co/bartowski/ai… lmstudio-community…
Tokens/sec29.610.8
First chunk264 ms44 ms
TTFT264 ms2.0 s
Load time3.8 s10.9 s
Memory usage8.4 GB0.0 GB
Memory %53%0%
HW Fit Score Breakdown
hf.co/bartowski/ai9star…
Speed
50/50
TTFT
20/20
Memory
24/30
lmstudio-community/gemm…
Speed
20/50
TTFT
17/20
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
lmstudio-community/gemm…
Reasoning
14/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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