hf.co/unsloth/gemma-4-E2B-it-GGUF:UD-Q8_K_XL
OLLAMA GGUFgemma4 · 4.65B · unknown
Aug 23, 2026 · Apple M1 Pro
qwopus3.6-27b-coder-compat-mtp
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
84 vs 88
Hardware Fit
99 vs 80
Quality Score
77 vs 91
Hardware
hf.co/unsloth/gemm… qwopus3.6-27b-code…
MachineMacBook ProASUS
CPUApple M1 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M1 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.6.2cachyos rolling
Archarm64x64
Power Modebalancedperformance
Performance
hf.co/unsloth/gemm… qwopus3.6-27b-code…
Tokens/sec48.080.8
First chunk167 ms6 ms
TTFT167 ms226 ms
Load time4.7 sN/A
Memory usage5.3 GB24.6 GB
Memory %33%81%
HW Fit Score Breakdown
hf.co/unsloth/gemma-4-E…
Speed
50/50
TTFT
20/20
Memory
29/30
qwopus3.6-27b-coder-com…
Speed
50/50
TTFT
20/20
Memory
10/30
Quality
hf.co/unsloth/gemma-4-E…
Reasoning
12/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
qwopus3.6-27b-coder-com…
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
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