Ornith-1.0-35B GGUF size and VRAM requirements
Ornith-1.0-35B-GGUF is a language model focused on general purpose & instruction. It is built on the qwen35moe architecture with a native context window of up to 262,144 tokens. The model is primarily recommended for general knowledge, document summarization, email drafting, language translation, and multi-turn conversational chat. Released under the mit license, it can be executed fully offline without sending data to external APIs.
Ornith-1.0-35B-GGUF is a Mixture-of-Experts model with 256 experts, of which 8 are active on each token. Routing only 8 of 256 experts makes it noticeably faster than a dense model of the same size — but every expert still has to be held in memory, so the numbers below are set by the full parameter count, not the active one. It is built from 40 transformer layers, a hidden size of 2,048, 16 attention heads. It uses a hybrid attention design: only 10 of its 40 layers keep a full KV cache, while the rest use linear attention with a constant-size state. Long contexts therefore cost far less memory than on a conventional model of this size.
To run deepreinforce-ai/Ornith-1.0-35B-GGUF locally at a 4,096-token context, its quantized versions need between 20.59 GB (Q4_K_M, lowest quality) and 65.49 GB (BF16, highest quality) of memory, weights plus KV cache and a system margin included. Context length drives that memory directly: at 4,096 tokens the KV cache for Ornith-1.0-35B-GGUF is about 0.08 GB, rising to roughly 5.0 GB at its full 262,144-token context. Shorter prompts free up memory for a higher-quality quantization.
For most users the best balance is Q5_K_M, needing about 23.91 GB. That means deepreinforce-ai/Ornith-1.0-35B-GGUF fits entirely in the VRAM of a 24 GB GPU or larger, running fully on the GPU.
Available GGUF quantizations for deepreinforce-ai/Ornith-1.0-35B-GGUF include Q4_K_M, Q5_K_M, Q6_K, Q8_0, BF16. The model supports a native context length of up to 262,144 tokens; a longer context grows the KV cache and the memory needed.
Recommended Use Cases & Local Setup
Ideal for: General knowledge, document summarization, email drafting, language translation, and multi-turn conversational chat.
Simple one-line CLI installation running silently in the background
Polished desktop client with one-click model downloads and GPU offloading
Open-source privacy-focused desktop assistant
GGUF file size and memory by quantization
Compare real GGUF weight sizes, estimated KV cache and total memory for Q4, Q5, Q8 and every quantization published in this repository.
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| Q4_K_M | 254659.13 | Excellent | 19.71 GB | 0.08 GB | 20.59 GB | 2.5 t/s | Offload |
| Q5_K_M | 297518.36 | Excellent | 23.03 GB | 0.08 GB | 23.91 GB | 2.2 t/s | Offload |
| Q6_K | 343056.28 | Excellent | 26.56 GB | 0.08 GB | 27.43 GB | — | Insufficient |
| Q8_0 | 443984.92 | Excellent | 34.37 GB | 0.08 GB | 35.25 GB | — | Insufficient |
| BF16 | 834676.45 | Excellent | 64.61 GB | 0.08 GB | 65.49 GB | — | Insufficient |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
What kind of model is deepreinforce-ai/Ornith-1.0-35B-GGUF?
deepreinforce-ai/Ornith-1.0-35B-GGUF is a language model, based on the qwen35moe architecture. It is released under the mit license and distributed as GGUF files for local inference.
Is deepreinforce-ai/Ornith-1.0-35B-GGUF a Mixture-of-Experts (MoE) model?
Yes. deepreinforce-ai/Ornith-1.0-35B-GGUF is a Mixture-of-Experts model with 256 experts, of which 8 are activated per token. That makes it faster than a dense model of the same size, but all 256 experts must be loaded into memory, so the VRAM/RAM it needs is driven by the total parameter count, not the active one.
How does deepreinforce-ai/Ornith-1.0-35B-GGUF handle long context?
deepreinforce-ai/Ornith-1.0-35B-GGUF uses a hybrid attention design: only 10 of its 40 layers keep a full KV cache, and the rest use linear attention with a constant-size state. Long contexts cost far less memory than on a conventional model of this size.
How much VRAM do you need to run deepreinforce-ai/Ornith-1.0-35B-GGUF?
You need about 23.91 GB of VRAM to run deepreinforce-ai/Ornith-1.0-35B-GGUF entirely on the GPU using the Q5_K_M quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run deepreinforce-ai/Ornith-1.0-35B-GGUF on an 8 GB GPU?
Partially. deepreinforce-ai/Ornith-1.0-35B-GGUF only fits on an 8 GB GPU by offloading part of it to system RAM (with Q5_K_M), which runs but is slower.
Can I run deepreinforce-ai/Ornith-1.0-35B-GGUF on a 16 GB GPU?
Partially. deepreinforce-ai/Ornith-1.0-35B-GGUF only fits on a 16 GB GPU by offloading part of it to system RAM (with Q8_0), which runs but is slower.
Can I run deepreinforce-ai/Ornith-1.0-35B-GGUF on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run deepreinforce-ai/Ornith-1.0-35B-GGUF fully on the GPU using Q5_K_M (about 23.91 GB).
What context length does deepreinforce-ai/Ornith-1.0-35B-GGUF support?
deepreinforce-ai/Ornith-1.0-35B-GGUF supports a native context length of up to 262,144 tokens. A longer context grows the KV cache, so it increases the memory needed to run the model.
What is the best quantization for deepreinforce-ai/Ornith-1.0-35B-GGUF?
For deepreinforce-ai/Ornith-1.0-35B-GGUF, a strong default is Q4_K_M, which needs about 20.59 GB and keeps most of the quality while roughly halving the memory versus 8-bit. With VRAM to spare, Q5_K_M or Q6_K add a little more quality; if you are tight on memory, a smaller quantization still runs. Pick the highest quantization that fits your VRAM.