qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

qwen35moe · 35B

THINKING MODEL

MacBook Pro (Apple M4 Max)

128 GB · macOS 26.5.2

Tested on August 19, 2026 · Submitted by Jujube

Top 13% Compare

Global Score

88 /100

Not Rec.

Hardware Fit

80/100

Quality

92/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: MacBook Pro
CPU: Apple M4 Max
Cores: 16 total (12 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 128 GB LPDDR5
GPU: Apple M4 Max
OS: macOS 26.5.2
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 76.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.6
First chunk latency Delay before the first streamed chunk arrives from runtime: 29 ms
Time to first token How fast the model starts responding — lower is better: 30.0 s
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 23.9 GB (19%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~958

Score breakdown

Speed

50/50

Time to first token

0/20

Memory

30/30

Quality

Reasoning

19/20

Coding

18/20

Instruction following

17/20

Structured output

14/15

Math

14/15

Multilingual

10/10

Category levels

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.12+1
Model format: GGUF
Hardware profile: HIGH-END
Result hash: a591cd04d69a5dc5c6cda99c696dc12a2eecc9f1fe1e9fdcc5104c72c651dc8d

Interpretation

Hardware fit: 80/100. Overall suitability: NOT RECOMMENDED (Global 88/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.

Disqualifiers

Time to first token too high: 30000ms (maximum: 13000ms for HIGH-END profile)

Bench Environment

Power: AC CPU load: avg 14% (peak 18%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest