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

qwen35moe · 35B

THINKING MODEL ECO MODE

Gigabyte Technology Co., Ltd. B550M AORUS PRO (AMD Ryzen 5 5600X 6-Core Processor)

47 GB · cachyos rolling

Tested on June 19, 2026

Top 6% Compare

Global Score

89 /100

Excellent

Hardware Fit

90/100

Quality

88/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPU: AMD Ryzen 5 5600X 6-Core Processor
Cores: 12 threads (6 cores)
Frequency: 3.7 GHz
RAM: 47 GB
GPU: AD106 [GeForce RTX 4060 Ti]
OS: cachyos rolling
Arch: x64
Power Mode: low-power

Performance

Tokens/sec Tokens generated per second — higher is better: 42.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±4.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 40 ms
Time to first token How fast the model starts responding — lower is better: 2.7 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: 21.9 GB (47%)
Total tokens Total number of tokens generated across all benchmark prompts: 1373
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~669

Score breakdown

Speed

50/50

Time to first token

14/20

Memory

26/30

Quality

Reasoning

19/20

Coding

16/20

Instruction following

14/20

Structured output

14/15

Math

15/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.16+1
Model format: GGUF
Hardware profile: BALANCED
Result hash: b70638494441b79ec3f1510cf0f355042274a34050ed472d67b2b0d71a429e09

Interpretation

Hardware fit: 90/100. Overall suitability: EXCELLENT (Global 89/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.
System was in low-power mode during this benchmark.

Bench Environment

Thermal: nominal CPU load: avg 49% (peak 61%)

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