Qwen3 8B Speculator.eagle3 — Hardware Requirements & GPU Compatibility
Chat
Qwen3 8B Speculator.eagle3 is a 1.0B-parameter open language model from RedHatAI in the Qwen 3 family. At Q4_K_M it needs about 0.67 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~978 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~107 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3 8B Speculator.eagle3
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 RedHatAI/Qwen3-8B-speculator.eagle3 --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 RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~349 tok/s
- generation speed
- Cost per 1M output tokens
- $0.049
- per 1M output tokens
How Much VRAM Does Qwen3 8B Speculator.eagle3 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.5 GB | 3.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~1365 tok/s | |
| 0.6 GB | 3.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~1191 tok/s | |
| 0.7 GB | 3.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~978 tok/s | |
| 0.8 GB | 3.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~819 tok/s | |
| 0.9 GB | 4 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~705 tok/s | |
| 1.1 GB | 4.2 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~585 tok/s | |
| 2.3 GB | 5.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~291 tok/s |
Selected Q4_K_M
4-bit medium quantization2.1GBat 16K context
- Weights
- 0.2 GB
- KV cache
- 1.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.9 GB free · ~978 tok/s
≥50 tok/s needs ≥51 GB/s · RTX 5090 ~1739, RTX 3090 Ti ~978
Which Hardware Can Run Qwen3 8B Speculator.eagle3?
Q4_K_M · 0.7 GBQwen3 8B Speculator.eagle3 (Q4_K_M) requires 0.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Qwen3 8B Speculator.eagle3, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.9 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~738Simulate output on RTX 3080RTX 2080 Ti~598Simulate output on RTX 2080 TiRTX 3070 Ti~590Simulate output on RTX 3070 TiM3*8 GB~107Simulate output on iMac 24" M3 (8 GB)Orin Nano~99Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~71Simulate output on iPhone 1720 GB
fits · 17.9 GB free · up to 32K ctx
1 GPU
RX 7900 XT~716Simulate output on RX 7900 XT32–40 GB
fits · 29.9 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1739Simulate output on RTX 5090M5 Max36 GB~481Simulate output on Mac Studio M5 Max (36 GB)M532 GB~161Simulate output on MacBook Air 13" M5 (32 GB)Orin~199Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~131Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen3 8B Speculator.eagle3
Qwen 3 family · 79 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM5 1BOpenBMB | — | 1.3 GB | ~662 | same size |
| InternVL3 5 1BOpenGVLab | — | 2.2 GB | ~936 | same size |
| Gemma 3 1B ITGoogle | — | 2.1 GB | ~993 | same size |
| TinyLlama 1.1B Chat v1.0TinyLlama | — | 1 GB | ~649 | same size |
| DiffuRefill 1BAsilarkness | — | 2.6 GB | ~252 | same size |
| Crowd V1Vxtzq | — | 3.7 GB | ~295 | same size |
Specifications
- Publisher
- RedHatAI
- Family
- Qwen 3
- Parameters
- 1.0B
- Architecture
- Eagle3Speculator
- Release Date
- 2025-09-19
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3 8B Speculator.eagle3 need?
Qwen3 8B Speculator.eagle3 requires 0.7 GB of VRAM at Q4_K_M, or 2.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.0B × 4.8 bits ÷ 8 = 0.6 GB
KV Cache + Overhead ≈ 0.1 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
What's the best quantization for Qwen3 8B Speculator.eagle3?
For Qwen3 8B Speculator.eagle3, Q4_K_M (0.7 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3 8B Speculator.eagle3 on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Qwen3 8B Speculator.eagle3. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Qwen3 8B Speculator.eagle3 locally?
Yes — Qwen3 8B Speculator.eagle3 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 8B Speculator.eagle3?
At Q4_K_M, Qwen3 8B Speculator.eagle3 can reach ~7164 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~978 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 ÷ 0.67 × 0.65 = ~7761 tok/s
Estimated speed at Q4_K_M (0.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3 8B Speculator.eagle3?
At Q4_K_M, the download is about 0.61 GB. The full-precision BF16 version is 2.04 GB. The smallest option (Q2_K) is 0.43 GB.
Which GPUs can run Qwen3 8B Speculator.eagle3?
52 consumer GPUs can run Qwen3 8B Speculator.eagle3 at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Qwen3 8B Speculator.eagle3?
163 devices with unified memory can run Qwen3 8B Speculator.eagle3 at Q4_K_M (0.7 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.