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

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 1, 2026 · Intel Xeon® E5-4620 0

Global Score
51 vs 65
Hardware Fit
31 vs 38
Quality Score
60 vs 76

Hardware

llama3.3:70b-instr… qwen3.5-35b-a3b-t4…
MachineDell Inc. Precision Tower 7910Dell Inc. PowerEdge R820
CPUIntel Xeon® E5-2637 v3Intel Xeon® E5-4620 0
Cores1664
RAM96 GB256 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

llama3.3:70b-instr… qwen3.5-35b-a3b-t4…
Tokens/sec1.73.4
First chunk5553 ms4210 ms
TTFT5.6 s4.2 s
Load time0.4 s45.1 s
Memory usage50.3 GB22.0 GB
Memory %53%9%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

qwen3.5-35b-a3b-t48-c8k…

Speed
3/50
TTFT
5/20
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

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
15/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Adequate 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