Back to leaderboard

ornith-1.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

Global Score
86 vs 78
Hardware Fit
92 vs 72
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/sec57.426.9
First chunk20 ms222 ms
TTFT367 ms222 ms
Load time51.1 s0.1 s
Memory usage66.6 GB15.4 GB
Memory %56%96%

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
2/30

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
14/20
Coding
19/20
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
View ornith-1.5-35b-a3b details | View gemma4:e4b-mlx details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest