ornith-1.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
gemma4:26b-nvfp4
OLLAMA GGUFnvfp4
May 25, 2026 · Apple M4 Pro
Global Score
86 vs 85
Hardware Fit
92 vs 80
Quality Score
84 vs 87
Hardware
ornith-1.5-35b-a3b gemma4:26b-nvfp4
MachineGMKtec EVO-X3MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3214
RAM120 GB48 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.4.1
Archx64arm64
Power Modebalancedbalanced
Performance
ornith-1.5-35b-a3b gemma4:26b-nvfp4
Tokens/sec57.465.7
First chunk20 ms233 ms
TTFT367 ms30.0 s
Load time51.1 s5.0 s
Memory usage66.6 GB15.2 GB
Memory %56%32%
HW Fit Score Breakdown
ornith-1.5-35b-a3b
Speed
50/50
TTFT
20/20
Memory
22/30
gemma4:26b-nvfp4
Speed
50/50
TTFT
0/20
Memory
30/30
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
gemma4:26b-nvfp4
Reasoning
17/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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