qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Jul 30, 2026 · Intel Core™ i9-14900K
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 20, 2026 · AMD RYZEN AI MAX+ 395
Global Score
35 vs 79
Hardware Fit
45 vs 100
Quality Score
30 vs 70
Hardware
qwen3.5:35b-a3b-q4… lfm2.5:latest
MachineMicro-Star International Co., Ltd. MS-7D98AZW GTR Pro
CPUIntel Core™ i9-14900KAMD RYZEN AI MAX+ 395
Cores3232
RAM128 GB125 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Radeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
qwen3.5:35b-a3b-q4… lfm2.5:latest
Tokens/sec16.7134.4
First chunk781 ms226 ms
TTFT30.0 s226 ms
Load time19.9 s1.8 s
Memory usage21.8 GB6.9 GB
Memory %17%6%
HW Fit Score Breakdown
qwen3.5:35b-a3b-q4_K_M
Speed
15/50
TTFT
0/20
Memory
30/30
lfm2.5:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:35b-a3b-q4_K_M
Reasoning
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor 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