llama3.3:70b-instruct-q4_K_M
OLLAMA GGUFllama · 70.6B · Q4_K_M
Aug 20, 2026 · Intel Xeon® E5-2637 v3
codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
51 vs 76
Hardware Fit
31 vs 91
Quality Score
60 vs 69
Hardware
llama3.3:70b-instr… codestral:latest
MachineDell Inc. Precision Tower 7910Gigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUIntel Xeon® E5-2637 v3Intel Core™ i5-14400F
Cores1616
RAM96 GB32 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060NVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
llama3.3:70b-instr… codestral:latest
Tokens/sec1.727.4
First chunk5553 ms86 ms
TTFT5.6 s86 ms
Load time0.4 s7.2 s
Memory usage50.3 GB12.6 GB
Memory %53%40%
HW Fit Score Breakdown
llama3.3:70b-instruct-q…
Speed
2/50
TTFT
5/20
Memory
24/30
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
Quality
llama3.3:70b-instruct-q…
Reasoning
17/20
Coding
6/20
Instruction
6/20
Structured
11/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Strong
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
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