ornith-1.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
86 vs 85
Hardware Fit
92 vs 95
Quality Score
84 vs 81
Hardware
ornith-1.5-35b-a3b gemma4:e4b-mlx
MachineGMKtec EVO-X3MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M2 Pro
Cores3210
RAM120 GB16 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M2 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
ornith-1.5-35b-a3b gemma4:e4b-mlx
Tokens/sec57.447.3
First chunk20 ms258 ms
TTFT367 ms258 ms
Load time51.1 s5.1 s
Memory usage66.6 GB7.9 GB
Memory %56%49%
HW Fit Score Breakdown
ornith-1.5-35b-a3b
Speed
50/50
TTFT
20/20
Memory
22/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
Quality
ornith-1.5-35b-a3b
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:e4b-mlx
Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong 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