qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3-30b-a3b-t16-c32k-instruct:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
13 vs 94
Hardware Fit
41 vs 100
Quality Score
1 vs 91
Hardware
qwen3.5:2b qwen3-30b-a3b-t16-…
MachineLENOVO 20L7CTO1WWDell Inc. Precision Tower 7910
CPUIntel Core™ i5-8350UIntel Xeon® E5-2637 v3
Cores816
RAM23 GB96 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSFedora Linux 43Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modelow-powerbalanced
Performance
qwen3.5:2b qwen3-30b-a3b-t16-…
Tokens/sec4.5116.0
First chunk1413 ms575 ms
TTFT31.1 s575 ms
Load time7.1 s10.2 s
Memory usage3.8 GB21.0 GB
Memory %16%22%
HW Fit Score Breakdown
qwen3.5:2b
Speed
11/50
TTFT
0/20
Memory
30/30
qwen3-30b-a3b-t16-c32k-…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:2b
Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
qwen3-30b-a3b-t16-c32k-…
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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