llmfan46OrnithQwen3_5MoeForConditionalGeneration

Ornith 1.0 35B Uncensored Heretic — Hardware Requirements & GPU Compatibility

Chat

Ornith 1.0 35B Uncensored Heretic is a 35.1B-parameter open language model from llmfan46 in the Ornith family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 21.45 GB of VRAM — see which GPUs and Macs can run it below.

35.1B params · dense262K contextMITJun 20261.6K downloads17 likes3.4K quant downloads

Based on Ornith 1.0 35B

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

B

Decent on a 24 GB GPU

Runs from 16 GB (Q2_K · 64K)Best on 24 GB (Q4_K_M · ~31 tok/s · 128K)Macs from 24 GB (Q4_K_S · ~11 tok/s)

MIT

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Ornith 1.0 35B Uncensored Heretic

One recommended way. Every other method, OS and quant is in the step-by-step guide.

Recommended

Ollama

one command · needs Ollama installed

$ollama run hf.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 2.5 GB free · 16K context

Download: Ornith-1.0-35B-uncensored-heretic-Q4_K_M.gguf21.23 GBllmfan46

install, OS, other quants

Other ways

each opens step-by-step

Run in cloud

Fits on RTX A6000 (48 GB) (26 GB headroom) · Q4_K_M

Generation speed: ~23 tok/s; generation speed
Cost per 1M output tokens: $3.93; per 1M output tokens

Deployon RunPodBest optionfrom $0.33/hr

Compare GPUs →

or

How Much VRAM Does Ornith 1.0 35B Uncensored Heretic Need?

Select a quantization level; the listed hardware adheres to it.

Quantization	VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
	15.3 GB	15.6 GB	16.6 GB	~14.9 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 256K context · ~43 tok/s
	17.5 GB	17.8 GB	18.8 GB	16.9 GB	3-bit medium — 3-bit medium quantization	Fits: 256K context · ~37 tok/s
	18.4 GB	18.6 GB	19.6 GB	18.3 GB	3-bit large — 3-bit large quantization	Fits: 256K context · ~36 tok/s
	20.1 GB	20.4 GB	21.4 GB	20 GB	4-bit small — 4-bit small quantization	Fits: 256K context · ~33 tok/s
	21.4 GB	21.7 GB	22.7 GB	21.2 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 128K context · ~31 tok/s
	24.5 GB	24.8 GB	25.8 GB	24 GB	5-bit small — 5-bit small quantization	Does not fit: needs 24.6 GB
	25.4 GB	25.7 GB	26.7 GB	24.8 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Does not fit: needs 25.5 GB
	29.4 GB	29.6 GB	30.6 GB	28.6 GB	6-bit, very good — 6-bit quantization, very good quality	Does not fit: needs 29.4 GB
	35.5 GB	35.7 GB	36.8 GB	36.9 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Does not fit: needs 35.6 GB
	70.6 GB	70.9 GB	71.9 GB	69.4 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 70.7 GB

est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

21.5GBat 16K context

Weights: 21.1 GB
KV cache: 0.2 GB
Overhead: 0.3 GB

Fits RTX 4090 (reference) · 2.5 GB free · ~31 tok/s

≥50 tok/s needs ≥1.65 TB/s · RTX 5090 ~54

Or rent RTX A6000 from $0.33/hr.

Which Hardware Can Run Ornith 1.0 35B Uncensored Heretic?

Q4_K_M · 21.4 GB

Ornith 1.0 35B Uncensored Heretic (Q4_K_M) requires 21.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 262K context window can add up to 2.6 GB, bringing total usage to 24.1 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090. 100 devices with unified memory can run Ornith 1.0 35B Uncensored Heretic, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8–12 GB · RTX 4060, RTX 3060 12GBDoesn't fit — smallest quant needs 15.4 GB8 GB tier →12 GB tier →

16 GB · RTX 5060 Ti 16GBQ2_K · 15.4 GB · ~19 tok/s · 64K15.4~1964K16 GB tier →

24 GB · RTX 4090referenceQ4_K_M · 21.5 GB · ~31 tok/s · 128K21.5~31128K24 GB tier →

Mac 32 GB · Mac Mini M4Q4_K_M · 21.5 GB · ~4 tok/s · 256K21.5~4256KMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 21.5 GB · ~18 tok/s · 256K21.5~18256KMacs →

Alternatives to Ornith 1.0 35B Uncensored Heretic

Ornith family · 11 models →

Similar models

6tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Qwen3.6 35B A3BAlibaba	106.8	22 GB	~151	same size
MiniCPM V 4.7 35B A3BOpenBMB	—	22.1 GB	~169	same size
Llm Jp 4.1 33B Thinkingllm-jp	—	22.5 GB	~35	same size
Agnes 3.0 FlashAgnes-AI	—	22.1 GB	~35	same size
Agents A1InternScience	—	21.5 GB	~171	same size
Intern S2 PreviewInternLM	—	73.2 GB	—needs > 24 GB	same size

Specifications

Publisher: llmfan46
Family: Ornith
Parameters: 35.1B
Architecture: Qwen3_5MoeForConditionalGeneration
Context Length: 262,144 tokens
Vocabulary Size: 248,320
Release Date: 2026-06-30
License: MIT

Resources

Frequently Asked Questions

How much VRAM does Ornith 1.0 35B Uncensored Heretic need?

Ornith 1.0 35B Uncensored Heretic requires 21.4 GB of VRAM at Q4_K_M, or 70.6 GB at BF16. Full 262K context adds up to 2.6 GB (24.1 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 35.1B × 4.8 bits ÷ 8 = 21.1 GB

KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 2.9 GB (at full 262K context)

VRAM usage by quantization

Q4_K_M

21.4 GB

Q4_K_M + full context

24.1 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Ornith 1.0 35B Uncensored Heretic?

Yes, at Q4_K_M (21.4 GB) or lower. Higher quantizations like Q5_K_S (24.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Ornith 1.0 35B Uncensored Heretic?

For Ornith 1.0 35B Uncensored Heretic, Q4_K_M (21.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (24.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.3 GB.

VRAM requirement by quantization

Q2_K

15.3 GB~75%

Q3_K_L

18.4 GB~86%

Q4_K_M ★

21.4 GB~89%

Q5_K_S

24.5 GB~92%

Q6_K

29.4 GB~95%

BF16

70.6 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Ornith 1.0 35B Uncensored Heretic on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Ornith 1.0 35B Uncensored Heretic, the smallest at Q4_K_S. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 21.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).

Can I run Ornith 1.0 35B Uncensored Heretic locally?

Yes — Ornith 1.0 35B Uncensored Heretic can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Ornith 1.0 35B Uncensored Heretic?

At Q4_K_M, Ornith 1.0 35B Uncensored Heretic can reach ~224 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~31 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 21.45 × 0.65 = ~242 tok/s

Estimated speed at Q4_K_M (21.4 GB)

NVIDIA B200

~242 tok/s

NVIDIA GeForce RTX 4090

~31 tok/s

NVIDIA B300

~242 tok/s

AMD Instinct MI350X

~224 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Ornith 1.0 35B Uncensored Heretic?

At Q4_K_M, the download is about 21.06 GB. The full-precision BF16 version is 70.21 GB. The smallest option (Q2_K) is 14.92 GB.

Which GPUs can run Ornith 1.0 35B Uncensored Heretic?

7 consumer GPUs can run Ornith 1.0 35B Uncensored Heretic at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.

Which devices can run Ornith 1.0 35B Uncensored Heretic?

100 devices with unified memory can run Ornith 1.0 35B Uncensored Heretic at Q4_K_M (21.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.

Run Ornith 1.0 35B Uncensored Heretic

21.5 GB VRAM at 16K context · fits the RTX 4090 (2.5 GB free)

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run hf.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF:Q4_K_M -c 16384 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve llmfan46/Ornith-1.0-35B-uncensored-heretic --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~77 GB of GPU memory.

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX A6000 (48 GB)CheapestCheapest26 GB free	~23 tok/s	$3.93	Deploy on RunPodfrom $0.33/hr (opens in new tab)	48 GB · 26 GB free · ~23 tok/s · $3.93 / 1M tokens
RTX PRO 4500 (32 GB)10 GB free	~27 tok/s	$3.47	Deploy on RunPodfrom $0.34/hr (opens in new tab)	32 GB · 10 GB free · ~27 tok/s · $3.47 / 1M tokens
A40 (48 GB)26 GB free	~21 tok/s	$4.61	Deploy on RunPodfrom $0.35/hr (opens in new tab)	48 GB · 26 GB free · ~21 tok/s · $4.61 / 1M tokens
RTX A6000 (48 GB)26 GB free	~23 tok/s	$4.81	Deploy on Vast.aifrom $0.40/hr (opens in new tab)	48 GB · 26 GB free · ~23 tok/s · $4.81 / 1M tokens
A40 (48 GB)26 GB free	~21 tok/s	$7.05	Deploy on Vast.aifrom $0.54/hr (opens in new tab)	48 GB · 26 GB free · ~21 tok/s · $7.05 / 1M tokens
A100 40GB18 GB free	~47 tok/s	$3.85	Deploy on Vast.aifrom $0.65/hr (opens in new tab)	18 GB free · ~47 tok/s · $3.85 / 1M tokens
RTX 5090 (32 GB)10 GB free	~54 tok/s	$3.53	Deploy on RunPodfrom $0.69/hr (opens in new tab)	32 GB · 10 GB free · ~54 tok/s · $3.53 / 1M tokens
L40S (48 GB)26 GB free	~26 tok/s	$8.50	Deploy on Vast.aifrom $0.80/hr (opens in new tab)	48 GB · 26 GB free · ~26 tok/s · $8.50 / 1M tokens

Compare GPUs →