Unsloth Ornith 1.5 35B A3B — Hardware Requirements & GPU Compatibility
Chat
Unsloth Ornith 1.5 35B A3B is a 35B-parameter open language model from peculiar-ragdoll in the Ornith family. At Q4_K_M it needs about 23.10 GB of VRAM — see which GPUs and Macs can run it below.
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Unsloth Ornith 1.5 35B A3B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve peculiar-ragdoll/Unsloth-Ornith-1.5-35B-A3B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on A40 (48 GB) (21 GB headroom) · Q4_K_M
- Generation speed
- ~143 tok/s
- generation speed
- Cost per 1M output tokens
- $0.68
- per 1M output tokens
How Much VRAM Does Unsloth Ornith 1.5 35B A3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.9 GB | 23.2 GB | 3-bit · i-quant — Importance-weighted 3-bit | Fits: 32K context · ~218 tok/s | |
| 16.4 GB | 24.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 16K context · ~209 tok/s | |
| 18.8 GB | 27.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~196 tok/s | |
| 20.7 GB | 29 GB | 4-bit · i-quant compact — Importance-weighted 4-bit, compact | Fits: 8K context · ~187 tok/s | |
| 21.7 GB | 30 GB | 4-bit small — 4-bit small quantization | Fits: 8K context · ~183 tok/s | |
| 23.1 GB | 31.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 4K context · ~177 tok/s | |
| 27.4 GB | 35.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 31.3 GB | |
| 31.8 GB | 40.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 35.6 GB | |
| 38.5 GB | 46.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 42.4 GB | |
| 77 GB | 85.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 80.9 GB |
Selected Q4_K_M
4-bit medium quantization27.0GBat 16K context
- Weights
- 22.3 GB
- KV cache
- 4.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · fits up to 4K context · ~177 tok/s
Or .
Which Hardware Can Run Unsloth Ornith 1.5 35B A3B?
Q4_K_M · 23.1 GBUnsloth Ornith 1.5 35B A3B (Q4_K_M) requires 23.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 31+ GB is recommended. 7 GPUs can run it, including NVIDIA GeForce RTX 5090. 100 devices with unified memory can run Unsloth Ornith 1.5 35B A3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (36 GB).
20 GB
Q4_K_M · best fit IQ3_XXS (18.8 GB)
1 GPU
RX 7900 XT~82Simulate output on RX 7900 XT32–40 GB
fits · 5.0 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~230Simulate output on RTX 5090M5 Max36 GB~64Simulate output on Mac Studio M5 Max (36 GB)M532 GB~36Simulate output on MacBook Air 13" M5 (32 GB)Orin~57Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~37Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Unsloth Ornith 1.5 35B A3B
Ornith family · 12 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | same size |
| Sage A1.5InternScience | — | 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 |
Specifications
- Publisher
- peculiar-ragdoll
- Family
- Ornith
- Parameters
- 35B
- Active parameters
- 3B per token
- Release Date
- 2026-08-20
- License
- MIT
Frequently Asked Questions
How much VRAM does Unsloth Ornith 1.5 35B A3B need?
Unsloth Ornith 1.5 35B A3B requires 23.1 GB of VRAM at Q4_K_M, or 77 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 35B × 4.8 bits ÷ 8 = 21 GB
KV Cache + Overhead ≈ 2.1 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.
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Unsloth Ornith 1.5 35B A3B?
Yes, at Q4_K_M (23.1 GB) or lower. Higher quantizations like Q5_K_M (27.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Unsloth Ornith 1.5 35B A3B?
For Unsloth Ornith 1.5 35B A3B, Q4_K_M (23.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (27.4 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XXS at 14.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Unsloth Ornith 1.5 35B A3B on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Unsloth Ornith 1.5 35B A3B, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 23.1 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run Unsloth Ornith 1.5 35B A3B locally?
Yes — Unsloth Ornith 1.5 35B A3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Unsloth Ornith 1.5 35B A3B?
At Q4_K_M, Unsloth Ornith 1.5 35B A3B can reach ~100 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~177 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 2.0 GB active ÷ (8000 × 0.65) = 0.38 ms, plus 48 layers × 0.055 ms = 2.64 ms, so 1000 ÷ 3.02 ms = ~331 tok/s
Estimated speed at Q4_K_M (23.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Unsloth Ornith 1.5 35B A3B?
At Q4_K_M, the download is about 21.00 GB. The full-precision BF16 version is 70.00 GB. The smallest option (IQ3_XXS) is 13.56 GB.
Which GPUs can run Unsloth Ornith 1.5 35B A3B?
7 consumer GPUs can run Unsloth Ornith 1.5 35B A3B at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
Which devices can run Unsloth Ornith 1.5 35B A3B?
100 devices with unified memory can run Unsloth Ornith 1.5 35B A3B at Q4_K_M (23.1 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.