codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
nvidia-nemotron-3-nano-4b
LM-STUDIO GGUFnemotron_h · 4B · Q4_K_M
Oct 24, 2026 · Intel Core™ i3-9100F
Global Score
76 vs 83
Hardware Fit
91 vs 100
Quality Score
69 vs 75
Hardware
codestral:latest nvidia-nemotron-3-…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Gigabyte Technology Co., Ltd. H310M S2 2.0
CPUIntel Core™ i5-14400FIntel Core™ i3-9100F
Cores164
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 5060 TiVirtual Desktop Monitor, NVIDIA GeForce GTX 1650
OSMicrosoft Windows 11 Professionnel 10.0.26200Майкрософт Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
codestral:latest nvidia-nemotron-3-…
Tokens/sec27.428.9
First chunk86 ms22 ms
TTFT86 ms580 ms
Load time7.2 sN/A
Memory usage12.6 GB3.8 GB
Memory %40%24%
HW Fit Score Breakdown
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
nvidia-nemotron-3-nano-4b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
codestral:latest
Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
nvidia-nemotron-3-nano-4b
Reasoning
15/20
Coding
12/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest