llama3.3:70b-instruct-q4_K_M
OLLAMA GGUFllama · 70.6B · Q4_K_M
Aug 20, 2026 · Intel Xeon® E5-2637 v3
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
51 vs 80
Hardware Fit
31 vs 60
Quality Score
60 vs 88
Hardware
llama3.3:70b-instr… qwen3-coder:30b
MachineDell Inc. Precision Tower 7910ASUS
CPUIntel Xeon® E5-2637 v3Intel Gen Intel® Core™ i7-12700K
Cores1620
RAM96 GB96 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Parsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
llama3.3:70b-instr… qwen3-coder:30b
Tokens/sec1.714.7
First chunk5553 ms796 ms
TTFT5.6 s796 ms
Load time0.4 s0.2 s
Memory usage50.3 GB17.9 GB
Memory %53%19%
HW Fit Score Breakdown
llama3.3:70b-instruct-q…
Speed
2/50
TTFT
5/20
Memory
24/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
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
qwen3-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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