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

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
35 vs 36
Hardware Fit
45 vs 100
Quality Score
30 vs 8

Hardware

qwen3.5:35b-a3b-q4… qwen36-distill-apex
MachineMicro-Star International Co., Ltd. MS-7D98MacBook Pro
CPUIntel Core™ i9-14900KApple M5 Max
Cores3218
RAM128 GB64 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Apple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… qwen36-distill-apex
Tokens/sec16.755.2
First chunk781 ms210 ms
TTFT30.0 s210 ms
Load time19.9 s4.8 s
Memory usage21.8 GB0.9 GB
Memory %17%2%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

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

qwen36-distill-apex

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

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

qwen36-distill-apex

Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3.5:35b-a3b-q4… details | View qwen36-distill-apex 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