llama3.3:70b-instruct-q4_K_M
OLLAMA GGUFllama · 70.6B · Q4_K_M
Aug 20, 2026 · Intel Xeon® E5-2637 v3
hf.co/openbmb/MiniCPM5-1B-GGUF:F16
OLLAMA GGUFllama · 1.08B · F16
Aug 22, 2026 · Apple M1 Pro
Global Score
51 vs 62
Hardware Fit
31 vs 100
Quality Score
60 vs 45
Hardware
llama3.3:70b-instr… hf.co/openbmb/Mini…
MachineDell Inc. Precision Tower 7910MacBook Pro
CPUIntel Xeon® E5-2637 v3Apple M1 Pro
Cores1610
RAM96 GB16 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M1 Pro
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
llama3.3:70b-instr… hf.co/openbmb/Mini…
Tokens/sec1.788.6
First chunk5553 ms165 ms
TTFT5.6 s165 ms
Load time0.4 s0.1 s
Memory usage50.3 GB3.9 GB
Memory %53%25%
HW Fit Score Breakdown
llama3.3:70b-instruct-q…
Speed
2/50
TTFT
5/20
Memory
24/30
hf.co/openbmb/MiniCPM5-…
Speed
50/50
TTFT
20/20
Memory
30/30
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
hf.co/openbmb/MiniCPM5-…
Reasoning
16/20
Coding
9/20
Instruction
4/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Strong Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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