Back to leaderboard

llama3.3:70b-instruct-q4_K_M

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Aug 20, 2026 · Intel Xeon® E5-2637 v3

Qwen3.8-27B-UD-Q3_K_XL

OLLAMA GGUF

llama · 27.3B · Q4_K

Excellent

Aug 23, 2026 · Intel Gen Intel® Core™ i5-12600K

Global Score
51 vs 90
Hardware Fit
31 vs 97
Quality Score
60 vs 87

Hardware

llama3.3:70b-instr… Qwen3.8-27B-UD-Q3_…
MachineDell Inc. Precision Tower 7910
CPUIntel Xeon® E5-2637 v3Intel Gen Intel® Core™ i5-12600K
Cores1616
RAM96 GB31 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060AlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

llama3.3:70b-instr… Qwen3.8-27B-UD-Q3_…
Tokens/sec1.739.0
First chunk5553 ms305 ms
TTFT5.6 s305 ms
Load time0.4 s0.0 s
Memory usage50.3 GB12.5 GB
Memory %53%41%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

Speed
2/50
TTFT
5/20
Memory
24/30

Qwen3.8-27B-UD-Q3_K_XL

Speed
50/50
TTFT
20/20
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

Qwen3.8-27B-UD-Q3_K_XL

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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