Unsloth-Ornith-1.5-35B-A3B

Qwen family · 36.0B params

1recorded run

53.3best tok/s

0verified

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 24, 2026. What these labels mean.

What the Unsloth-Ornith-1.5-35B-A3B numbers mean

The fastest result on our board is 53.3 output tok/s on an T4 at Q2_K_XL with a 2048-token context. That is about 18.8 ms per generated token — 500 tokens takes roughly 9.4 seconds. Prompt processing on the same record runs at 674.1 tok/s, so a 2,000-token prompt is read in about 3.0 seconds.

How much VRAM does Unsloth-Ornith-1.5-35B-A3B need?

Unsloth-Ornith-1.5-35B-A3B has 36.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Quantisation	Estimated VRAM	Smallest card that fits
Q4_K_M (4-bit)	24.1 GB	32 GB
Q8_0 (8-bit)	44.8 GB	64 GB
FP16 (16-bit)	83.6 GB	141 GB

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Fastest GPUs for this model (best tok/s)

T453.3

Models with a similar footprint

Model	Params	Q4_K_M weights
Ornith-1.5-35B-A3B	36B	20.2 GB
Ornith-1.5-35B-A3B-GPTQ-Int4-sym-G128-MTP-BF16-MixedCal-v2	36B	20.2 GB
Ornith-1.5-35B-A3B-MTP	36B	20.2 GB
Qwen3.6-35B-A3B	36B	20.2 GB
Qwen3.6-35B-A3B-abliterated-v4	36B	20.2 GB
Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved	36B	20.2 GB

Ranked by distance from Unsloth-Ornith-1.5-35B-A3B's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
T4 · 16 GB	Unsloth-Ornith-1.5-35B-A3B	Q2_K_XL	llama.cpp —	2048	53.3 …	674.1	—	src