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

huihui_ai/Qwen3.8-abliterated:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 25, 2026 · AMD RYZEN AI MAX+ 395

Global Score
51 vs 80
Hardware Fit
31 vs 65
Quality Score
60 vs 87

Hardware

llama3.3:70b-instr… huihui_ai/Qwen3.8-…
MachineDell Inc. Precision Tower 7910AZW GTR Pro
CPUIntel Xeon® E5-2637 v3AMD RYZEN AI MAX+ 395
Cores1632
RAM96 GB125 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Radeon 8060S
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

llama3.3:70b-instr… huihui_ai/Qwen3.8-…
Tokens/sec1.717.5
First chunk5553 ms597 ms
TTFT5.6 s597 ms
Load time0.4 s7.1 s
Memory usage50.3 GB17.4 GB
Memory %53%14%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

huihui_ai/Qwen3.8-ablit…

Speed
16/50
TTFT
19/20
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

huihui_ai/Qwen3.8-ablit…

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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