Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

smollm2-1.7b-instruct

LM-STUDIO MLX

llama · 1.7B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
59 vs 65
Hardware Fit
69 vs 99
Quality Score
54 vs 51

Hardware

qwen3.5:35b-a3b smollm2-1.7b-instr…
MachineMacBook ProMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM48 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 26.3.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b smollm2-1.7b-instr…
Tokens/sec30.528.5
First chunk333 ms393 ms
TTFT30.0 s393 ms
Load time9.8 sN/A
Memory usage25.1 GB3.2 GB
Memory %52%10%

HW Fit Score Breakdown

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

smollm2-1.7b-instruct

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong

smollm2-1.7b-instruct

Reasoning
10/20
Coding
10/20
Instruction
13/20
Structured
11/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
View qwen3.5:35b-a3b details | View smollm2-1.7b-instr… 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