Ornith 1.0 35B-A3B on NVIDIA RTX PRO 4000 Blackwell SFF Edition

Can the NVIDIA RTX PRO 4000 Blackwell SFF Edition run Ornith 1.0 35B-A3B?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q4_K_M it needs about 23.9 GB of 24.0 GB usable, with an estimated speed of 111 tok/s.

Best quant: Q4_K_M
Generation speed: 111 tok/s
Prompt processing: 5,760 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 12K

Best app to run it on the NVIDIA RTX PRO 4000 Blackwell SFF Edition

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Ornith 1.0 35B-A3B in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Ornith 1.0 35B-A3B in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Ornith 1.0 35B-A3B

Recommended for the NVIDIA RTX PRO 4000 Blackwell SFF Edition: Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M file (opens in a new tab)

huggingface.co/ornith-ai/Ornith-1.0-35B-GGUF (opens in a new tab)

ollama run hf.co/ornith-ai/Ornith-1.0-35B-GGUF:Q4_K_M

Original weights · Hugging Face

Full-precision files from DeepReinforce, for fine-tuning, vLLM, Transformers.

huggingface.co/ornith-ai/Ornith-1.0-35B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs welltight fit: How well it runs on the NVIDIA RTX PRO 4000 Blackwell SFF Edition: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	38.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	92.0 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA RTX PRO 4000 Blackwell SFF Edition

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	16.3 GB	24.0 GB	152 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	19.6 GB	24.0 GB	131 tok/s	Runs great	74Great quality (A) · 74 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	23.9 GB	24.0 GB	111 tok/s	Runs welltight fit	84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	27.5 GB	24.0 GB	64.6 tok/s	Runs welloffloads to RAM	86Excellent quality (A+) · 86 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	31.4 GB	24.0 GB	43.4 tok/s	Runs welloffloads to RAM	88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	40.1 GB	24.0 GB	24.6 tok/s	Slowheavy RAM offload	89Excellent quality (A+) · 89 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	73.9 GB	24.0 GB	—	Won't run	89Excellent quality (A+) · 89 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

89Excellent quality (A+) · 89 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell F16 · 98.2 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q6_K · 72.3 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q6_K · 90.1 tok/s · Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q5_K_M · 62.2 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 179 tok/s · Runs well (tight fit)
89Excellent quality (A+) · 89 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) F16 · 51.3 tok/s · Runs great

Quick answers

How much memory does Ornith 1.0 35B-A3B need on the NVIDIA RTX PRO 4000 Blackwell SFF Edition 24GB?

At Q4_K_M it needs about 23.9 GB. The NVIDIA RTX PRO 4000 Blackwell SFF Edition 24GB has 24.0 GB usable.

How fast is Ornith 1.0 35B-A3B on the NVIDIA RTX PRO 4000 Blackwell SFF Edition 24GB?

About 111 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Ornith 1.0 35B-A3B should I use on the NVIDIA RTX PRO 4000 Blackwell SFF Edition 24GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.