hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 26, 2026 · Apple M1 Pro
qwen3-vl:30b
OLLAMA GGUFqwen3vlmoe · 31.1B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
66 vs 80
Hardware Fit
100 vs 98
Quality Score
52 vs 72
Hardware
hf.co/empero-ai/Qw… qwen3-vl:30b
MachineMacBook ProASUS
CPUApple M1 ProIntel Core™ Ultra 9 285K
Cores1024
RAM16 GB47 GB
GPUApple M1 ProNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… qwen3-vl:30b
Tokens/sec40.2208.9
First chunk101 ms102 ms
TTFT101 ms684 ms
Load time2.6 s0.1 s
Memory usage4.7 GB22.0 GB
Memory %30%47%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-vl:30b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
hf.co/empero-ai/Qwen3.8…
Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
qwen3-vl:30b
Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak 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