Back to leaderboard

qwen3.5:9b-mlx

OLLAMA GGUF

nvfp4

Excellent

Aug 25, 2026 · Apple M1 Pro

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Sep 6, 2026 · Intel Xeon® E5-4650 v2

Global Score
84 vs 81
Hardware Fit
94 vs 63
Quality Score
80 vs 88

Hardware

qwen3.5:9b-mlx qwen3.5-35b-a3b-t4…
MachineMacBook ProDell Inc. PowerEdge R820
CPUApple M1 ProIntel Xeon® E5-4650 v2
Cores1080
RAM16 GB256 GB
GPUApple M1 ProMicrosoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OSmacOS 26.6.2Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:9b-mlx qwen3.5-35b-a3b-t4…
Tokens/sec25.017.2
First chunk357 ms845 ms
TTFT357 ms845 ms
Load time3.8 s103.1 s
Memory usage8.4 GB21.9 GB
Memory %52%9%

HW Fit Score Breakdown

qwen3.5:9b-mlx

Speed
50/50
TTFT
20/20
Memory
24/30

qwen3.5-35b-a3b-t48-c8k…

Speed
16/50
TTFT
17/20
Memory
30/30

Quality

qwen3.5:9b-mlx

Reasoning
16/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5-35b-a3b-t48-c8k…

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:9b-mlx details | View qwen3.5-35b-a3b-t4… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest