Community performance summary

Ornith 1.5 35B

4 GPU configurations measured with this model. Compare hardware differences, quantizations and every recorded result.

7 signed runs · 0 verified · 4 testers
Median prompt665.15tok/s · 132.87 to 1602.21
Median generation42.78tok/s · 12.47 to 75.5
Configurations4BF16 · Q4_K_M · Q5_K_M
Last observedOct 12GCN / Vega + RDNA 2 · RDNA · RDNA 1

What the results show

One clear view.
Every recorded run.

Measurements from comparable hardware and models are presented together. Medians show typical performance, while every signed run remains available below for inspection and sharing.

Hardware tested4 groups
AMD Radeon Pro W5700X ×21 run→AMD Radeon Pro Vega II + AMD Radeon PRO W6800X Duo2 runs→AMD Radeon Pro 5500M2 runs→AMD Radeon GFX10, 16 GB2 runs→
macOS

macOS 15.7.5 Sequoia · macOS 15.7.9 Sequoia · macOS 26.6.2 Tahoe · macOS 26.7.1 Tahoe

Recorded evidence

Inspect every run.

Open any result to review its exact hardware, model configuration, measurements and submission details.

1 to 8 of 7 configurations

Verified benchmark Community submission
Model / quantHardwareArchitecturePromptGenerationSource
Ornith 1.5 35BUD-IQ3_XXS · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA
1602.21tok/s
75.5tok/s
Quad849Sep 4, 2026
Ornith 1.5 35BUD-IQ3_XXS · MoE · Signed ToshLLM app · ncmoe 1 · amd-gpu · Metal · comparison
RDNA
1105.37tok/s
66.28tok/s
Quad849Sep 4, 2026
Ornith 1.5 35BQ5_K_M · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
RDNA 1
791.23tok/s
59.61tok/s
HypabolicOct 12, 2026
Ornith 1.5 35BBF16 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
519.13tok/s
42.78tok/s
threadedSep 14, 2026
Ornith 1.5 35BBF16 · MoE · Signed ToshLLM app · amd-gpu · Metal · comparison
GCN / Vega + RDNA 2
665.15tok/s
23.72tok/s
threadedSep 15, 2026
Ornith 1.5 35BQ4_K_M · MoE · Signed ToshLLM app · ncmoe 30 · amd-gpu · Metal · comparison
RDNA 1
138.8tok/s
13.19tok/s
ToshLLM communitySep 10, 2026
Ornith 1.5 35BQ4_K_M · MoE · Signed ToshLLM app · ncmoe 32 · amd-gpu · Metal · comparison
RDNA 1
132.87tok/s
12.47tok/s
ToshLLM communitySep 10, 2026