qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Jul 30, 2026 · Intel Core™ i9-14900K
gemma3:1b
OLLAMA GGUFgemma3 · 999.89M · Q4_K_M
Feb 28, 2026 · Apple M4
Global Score
35 vs 68
Hardware Fit
45 vs 98
Quality Score
30 vs 55
Hardware
qwen3.5:35b-a3b-q4… gemma3:1b
MachineMicro-Star International Co., Ltd. MS-7D98MacBook Air
CPUIntel Core™ i9-14900KApple M4
Cores3210
RAM128 GB32 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Apple M4
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedunknown
Performance
qwen3.5:35b-a3b-q4… gemma3:1b
Tokens/sec16.739.5
First chunk781 msN/A
TTFT30.0 s333 ms
Load time19.9 s1.6 s
Memory usage21.8 GB1.3 GB
Memory %17%4%
HW Fit Score Breakdown
qwen3.5:35b-a3b-q4_K_M
Speed
15/50
TTFT
0/20
Memory
30/30
gemma3:1b
Speed
40/50
TTFT
30/20
Memory
28/30
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
gemma3:1b
Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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