Back to leaderboard

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

OLLAMA GGUF

nemotron_h_moe · 74.0B · IQ2_XXS

Excellent

Oct 16, 2026 · AMD RYZEN AI MAX+ 395

qwopus3.6-27b-coder-compat-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
90 vs 88
Hardware Fit
96 vs 80
Quality Score
87 vs 91

Hardware

nemotron-3.5-bolt:… qwopus3.6-27b-code…
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 7800X3D 8-Core Processor
Cores3216
RAM125 GB31 GB
GPURadeon 8060SNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.5 LTScachyos rolling
Archx64x64
Power Modeperformanceperformance

Performance

nemotron-3.5-bolt:… qwopus3.6-27b-code…
Tokens/sec49.942.9
First chunk370 ms32 ms
TTFT370 ms413 ms
Load time7.6 sN/A
Memory usage3.9 GB24.6 GB
Memory %3%81%

HW Fit Score Breakdown

nemotron-3.5-bolt:74b-a…

Speed
46/50
TTFT
20/20
Memory
30/30

qwopus3.6-27b-coder-com…

Speed
50/50
TTFT
20/20
Memory
10/30

Quality

nemotron-3.5-bolt:74b-a…

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwopus3.6-27b-coder-com…

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View nemotron-3.5-bolt:… details | View qwopus3.6-27b-code… 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