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

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex-mtp

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
51 vs 89
Hardware Fit
31 vs 90
Quality Score
60 vs 88

Hardware

llama3.3:70b-instr… qwen3.6-35b-a3b-cl…
MachineDell Inc. Precision Tower 7910Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Xeon® E5-2637 v3AMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM96 GB47 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060AD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 10 Pro 10.0.19045cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

llama3.3:70b-instr… qwen3.6-35b-a3b-cl…
Tokens/sec1.742.2
First chunk5553 ms40 ms
TTFT5.6 s2.7 s
Load time0.4 sN/A
Memory usage50.3 GB21.9 GB
Memory %53%47%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
14/20
Memory
26/30

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

qwen3.6-35b-a3b-claude-…

Reasoning
19/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View llama3.3:70b-instr… details | View qwen3.6-35b-a3b-cl… details

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