Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Aug 22, 2026 · Intel Xeon® E5-2637 v3

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
82 vs 68
Hardware Fit
69 vs 91
Quality Score
87 vs 58

Hardware

qwen3.5:35b-a3b-q4… qwen3.5:4b-mlx
MachineDell Inc. Precision Tower 7910MacBook Pro
CPUIntel Xeon® E5-2637 v3Apple M1 Pro
Cores1610
RAM96 GB16 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M1 Pro
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… qwen3.5:4b-mlx
Tokens/sec20.442.2
First chunk1362 ms201 ms
TTFT1.4 s4.4 s
Load time34.2 s0.0 s
Memory usage22.7 GB3.8 GB
Memory %24%24%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
23/50
TTFT
16/20
Memory
30/30

qwen3.5:4b-mlx

Speed
50/50
TTFT
11/20
Memory
30/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
17/20
Coding
17/20
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

qwen3.5:4b-mlx

Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
View qwen3.5:35b-a3b-q4… details | View qwen3.5:4b-mlx 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