qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Jul 30, 2026 · Intel Core™ i9-14900K
gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
35 vs 72
Hardware Fit
45 vs 71
Quality Score
30 vs 72
Hardware
qwen3.5:35b-a3b-q4… gemma4:e2b
MachineMicro-Star International Co., Ltd. MS-7D98Dell Inc. Inspiron 15 3530
CPUIntel Core™ i9-14900KIntel Gen Intel® Core™ i7-1355U
Cores3212
RAM128 GB31 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Raptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
qwen3.5:35b-a3b-q4… gemma4:e2b
Tokens/sec16.710.8
First chunk781 ms1408 ms
TTFT30.0 s1.4 s
Load time19.9 s6.0 s
Memory usage21.8 GB7.2 GB
Memory %17%23%
HW Fit Score Breakdown
qwen3.5:35b-a3b-q4_K_M
Speed
15/50
TTFT
0/20
Memory
30/30
gemma4:e2b
Speed
21/50
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
gemma4:e2b
Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong 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