ornith-1.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3.5-35b-a3b-mtp
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
86 vs 77
Hardware Fit
92 vs 51
Quality Score
84 vs 88
Hardware
ornith-1.5-35b-a3b qwen3.5-35b-a3b-mtp
MachineGMKtec EVO-X3Docker Container
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i9-11900H
Cores3216
RAM120 GB15 GB
GPUAMD Radeon(TM) 8060S GraphicsTigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26300Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance
Performance
ornith-1.5-35b-a3b qwen3.5-35b-a3b-mtp
Tokens/sec57.47.8
First chunk20 ms30 ms
TTFT367 ms5.6 s
Load time51.1 s32.5 s
Memory usage66.6 GB0.0 GB
Memory %56%0%
HW Fit Score Breakdown
ornith-1.5-35b-a3b
Speed
50/50
TTFT
20/20
Memory
22/30
qwen3.5-35b-a3b-mtp
Speed
14/50
TTFT
7/20
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
qwen3.5-35b-a3b-mtp
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong 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