nemotron-3.5-bolt:74b-a9b-iq2

nemotron_h_moe · 74.0B · IQ2_XXS

AZW GTR Pro (AMD RYZEN AI MAX+ 395)

125 GB · Ubuntu 24.04.5 LTS

Tested on October 16, 2026

Top 6% Compare

Global Score

90 /100

Excellent

Hardware Fit

96/100

Quality

87/100

Get this model

🦙

Ollama

ollama pull nemotron-3.5-bolt:74b-a9b-iq2

View on Ollama Library

ollama.com/library/nemotron-3.5-bolt

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: AZW GTR Pro
CPU: AMD RYZEN AI MAX+ 395
Cores: 32 threads (16 cores)
Frequency: 3 GHz
RAM: 125 GB
GPU: Radeon 8060S
OS: Ubuntu 24.04.5 LTS
Arch: x64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 49.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±9.7
First chunk latency Delay before the first streamed chunk arrives from runtime: 370 ms
Time to first token How fast the model starts responding — lower is better: 370 ms
Load time Time to load the model into memory before inference: 7.6 s
Memory usage RAM consumed during inference — percentage of total system memory: 3.9 GB (3%)
Total tokens Total number of tokens generated across all benchmark prompts: 1012

Score breakdown

Speed

46/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

15/20

Coding

18/20

Instruction following

16/20

Structured output

15/15

Math

13/15

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: Ollama 0.40.5
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 4b5592d18eaf0ba253037bf11816623b591e69e1cc49bebdfb2cc2ec39a83de0

Interpretation

Hardware fit: 96/100. Overall suitability: EXCELLENT (Global 90/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Thermal: nominal CPU load: avg 24% (peak 31%)

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