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

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score
35 vs 58
Hardware Fit
45 vs 82
Quality Score
30 vs 48

Hardware

qwen3.5:35b-a3b-q4… qwen3:14b
MachineMicro-Star International Co., Ltd. MS-7D98MacBook Pro
CPUIntel Core™ i9-14900KApple M1 Max
Cores3210
RAM128 GB32 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Apple M1 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… qwen3:14b
Tokens/sec16.724.4
First chunk781 ms294 ms
TTFT30.0 s7.9 s
Load time19.9 s3.7 s
Memory usage21.8 GB13.8 GB
Memory %17%43%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

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

qwen3:14b

Speed
47/50
TTFT
5/20
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

qwen3:14b

Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
View qwen3.5:35b-a3b-q4… details | View qwen3:14b 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