qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Jul 30, 2026 · Intel Core™ i9-14900K
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
35 vs 46
Hardware Fit
45 vs 61
Quality Score
30 vs 40
Hardware
qwen3.5:35b-a3b-q4… llama3.1:8b
MachineMicro-Star International Co., Ltd. MS-7D98NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i9-14900KCortex-A78AE
Cores326
RAM128 GB7 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Integrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5:35b-a3b-q4… llama3.1:8b
Tokens/sec16.77.8
First chunk781 ms1625 ms
TTFT30.0 s1.6 s
Load time19.9 s21.8 s
Memory usage21.8 GB5.2 GB
Memory %17%71%
HW Fit Score Breakdown
qwen3.5:35b-a3b-q4_K_M
Speed
15/50
TTFT
0/20
Memory
30/30
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
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
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak 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