Qwen3.8 27B DSpark — Hardware Requirements & GPU Compatibility
Chat
Qwen3.8 27B DSpark is a 27B-parameter open language model from RadixArk in the Qwen 3.8 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 16.55 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 16 GB (Q3_K_M · 64K)Best on 24 GB (Q4_K_M · ~40 tok/s · 256K)Macs from 16 GB (Q2_K · ~12 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3.8 27B DSpark
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/Anbeeld/Qwen3.8-27B-DSpark-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 7.1 GB free · 16K context
Download: Qwen3.8-27B-DSpark-Q4_K_M.gguf1.10 GBAnbeeld
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3090 (24 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~37 tok/s
- generation speed
- Cost per 1M output tokens
- $1.63
- per 1M output tokens
How Much VRAM Does Qwen3.8 27B DSpark Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 11.8 GB | 12.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~55 tok/s | |
| 13.5 GB | 14.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~49 tok/s | |
| 16.6 GB | 17.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~40 tok/s | |
| 19.6 GB | 20.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~33 tok/s | |
| 22.6 GB | 23.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~29 tok/s | |
| 27.4 GB | 28.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 27.7 GB | |
| 54.4 GB | 55.1 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 54.7 GB |
Selected Q4_K_M
4-bit medium quantization16.9GBat 16K context
- Weights
- 16.2 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 7.1 GB free · ~40 tok/s
≥50 tok/s needs ≥1.27 TB/s · RTX 5090 ~70
Which Hardware Can Run Qwen3.8 27B DSpark?
Q4_K_M · 16.6 GBQwen3.8 27B DSpark (Q4_K_M) requires 16.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 22+ GB is recommended. Using the full 262K context window can add up to 6.7 GB, bringing total usage to 23.2 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Qwen3.8 27B DSpark, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 3.1 GB free · up to 128K ctx
1 GPU
RX 7900 XT~29Simulate output on RX 7900 XT32–40 GB
fits · 15.1 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~70Simulate output on RTX 5090M5 Max36 GB~20Simulate output on Mac Studio M5 Max (36 GB)M532 GB~7Simulate output on MacBook Air 13" M5 (32 GB)Orin~8Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~5Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen3.8 27B DSpark
Qwen 3.8 family · 12 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | same size |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | same size |
| Gemma 3 27B ITGoogle | 79.4 | 21.7 GB | ~36 | same size |
| Gemma 2 27B ITGoogle | 72.7 | 19.5 GB | ~37 | same size |
| Gemma 4 26B A4BGoogle | — | 16.9 GB | ~153 | same size |
| Ariarhymes-ai | — | 20.2 GB | ~168 | same size |
Specifications
- Publisher
- RadixArk
- Family
- Qwen 3.8
- Parameters
- 27B
- Architecture
- DSparkDraftModel
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-08-14
- License
- Other
Frequently Asked Questions
How much VRAM does Qwen3.8 27B DSpark need?
Qwen3.8 27B DSpark requires 16.6 GB of VRAM at Q4_K_M, or 54.4 GB at BF16. Full 262K context adds up to 6.7 GB (23.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 27B × 4.8 bits ÷ 8 = 16.2 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 7 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Qwen3.8 27B DSpark?
Yes, at Q6_K (22.6 GB) or lower. Higher quantizations like Q8_0 (27.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen3.8 27B DSpark?
For Qwen3.8 27B DSpark, Q4_K_M (16.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (19.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 11.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3.8 27B DSpark on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Qwen3.8 27B DSpark, 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 16.6 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Qwen3.8 27B DSpark locally?
Yes — Qwen3.8 27B DSpark can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3.8 27B DSpark?
At Q4_K_M, Qwen3.8 27B DSpark can reach ~290 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~40 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 ÷ 16.55 × 0.65 = ~314 tok/s
Estimated speed at Q4_K_M (16.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3.8 27B DSpark?
At Q4_K_M, the download is about 16.20 GB. The full-precision BF16 version is 54.00 GB. The smallest option (Q2_K) is 11.47 GB.
Which GPUs can run Qwen3.8 27B DSpark?
8 consumer GPUs can run Qwen3.8 27B DSpark at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Qwen3.8 27B DSpark?
122 devices with unified memory can run Qwen3.8 27B DSpark at Q4_K_M (16.6 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.