qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 23, 2026 · Apple M1 Pro
Global Score
77 vs 66
Hardware Fit
75 vs 100
Quality Score
78 vs 52
Hardware
qwen3.5:9b hf.co/empero-ai/Qw…
MachineASUSMacBook Pro
CPUIntel Gen Intel® Core™ i7-13700KApple M1 Pro
Cores2410
RAM64 GB16 GB
GPUNVIDIA GeForce RTX 3070Apple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2
Archx64arm64
Power Modeunknownbalanced
Performance
qwen3.5:9b hf.co/empero-ai/Qw…
Tokens/sec30.540.4
First chunk291 ms93 ms
TTFT291 ms93 ms
Load time4.8 s2.7 s
Memory usage8.8 GB4.7 GB
Memory %14%30%
HW Fit Score Breakdown
qwen3.5:9b
Speed
34/50
TTFT
20/20
Memory
21/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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
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