qwen3.6:35b-a3b
OLLAMA GGUFqwen35moe · 35.5B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
86 vs 65
Hardware Fit
87 vs 73
Quality Score
86 vs 62
Hardware
qwen3.6:35b-a3b qwen3.5:4b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4AZW GTR Pro
CPUIntel Core™ i5-14400FAMD RYZEN AI MAX+ 395
Cores1632
RAM32 GB125 GB
GPUNVIDIA GeForce RTX 5060 TiAMD Radeon 8060S
OSMicrosoft Windows 11 Professionnel 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
qwen3.6:35b-a3b qwen3.5:4b
Tokens/sec59.545.7
First chunk380 ms180 ms
TTFT380 ms30.0 s
Load time24.6 s5.3 s
Memory usage20.9 GB16.2 GB
Memory %66%13%
HW Fit Score Breakdown
qwen3.6:35b-a3b
Speed
50/50
TTFT
20/20
Memory
17/30
qwen3.5:4b
Speed
43/50
TTFT
0/20
Memory
30/30
Quality
qwen3.6:35b-a3b
Reasoning
16/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5:4b
Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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