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

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
51 vs 90
Hardware Fit
31 vs 98
Quality Score
60 vs 86

Hardware

llama3.3:70b-instr… qwen3.6-35b-a3b-cl…
MachineDell Inc. Precision Tower 7910MacBook Pro
CPUIntel Xeon® E5-2637 v3Apple M5 Max
Cores1618
RAM96 GB64 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M5 Max
OSMicrosoft Windows 10 Pro 10.0.19045macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

llama3.3:70b-instr… qwen3.6-35b-a3b-cl…
Tokens/sec1.786.6
First chunk5553 ms13 ms
TTFT5.6 s143 ms
Load time0.4 sN/A
Memory usage50.3 GB23.9 GB
Memory %53%37%

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
20/20
Memory
28/30

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
18/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
12/15
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