Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
35 vs 89
Hardware Fit
45 vs 97
Quality Score
30 vs 86

Hardware

qwen3.5:35b-a3b-q4… qwen3.6:35b-mlx
MachineMicro-Star International Co., Ltd. MS-7D98MacBook Pro
CPUIntel Core™ i9-14900KApple M5 Max
Cores3218
RAM128 GB48 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Apple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… qwen3.6:35b-mlx
Tokens/sec16.7129.4
First chunk781 ms49 ms
TTFT30.0 s49 ms
Load time19.9 s0.0 s
Memory usage21.8 GB20.5 GB
Memory %17%43%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
0/20
Memory
30/30

qwen3.6:35b-mlx

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

qwen3.6:35b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:35b-a3b-q4… details | View qwen3.6:35b-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