Qwen3.5 0.8B — Hardware Requirements & GPU Compatibility
VisionFunctions
Qwen3.5-0.8B is the smallest model in Alibaba's Qwen3.5 generation, a dense sub-billion-parameter vision-language model using the same hybrid Gated DeltaNet and gated-attention design as the rest of the family. It is a post-trained, instruction-tuned release, and its publisher notes that at this scale it is best suited to prototyping, task-specific fine-tuning, and other research or development purposes rather than production chat. It supports a 262,144-token native context window and is released under the Apache 2.0 license. At under one billion parameters, it needs well under a gigabyte of memory at 4-bit, so it runs on essentially any modern laptop or GPU.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 256K)Best on 24 GB (Q4_K_M · ~753 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~82 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3.5 0.8B
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
ollama run hf.co/unsloth/Qwen3.5-0.8B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 23.1 GB free · 16K context
Download: Qwen3.5-0.8B-Q4_K_M.gguf0.53 GBunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~269 tok/s
- generation speed
- Cost per 1M output tokens
- $0.061
- per 1M output tokens
How Much VRAM Does Qwen3.5 0.8B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.7 GB | 0.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~910 tok/s | |
| 0.7 GB | 0.9 GB | 3-bit small — 3-bit small quantization | Fits: 256K context · ~898 tok/s | |
| 0.8 GB | 0.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~840 tok/s | |
| 0.8 GB | 0.9 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 256K context · ~829 tok/s | |
| 0.9 GB | 1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~753 tok/s | |
| 1.0 GB | 1.1 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~676 tok/s | |
| 1.1 GB | 1.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~612 tok/s | |
| 1.2 GB | 1.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~537 tok/s |
Selected Q4_K_M
4-bit medium quantization0.9GBat 16K context
- Weights
- 0.5 GB
- KV cache
- 0.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.1 GB free · ~753 tok/s
≥50 tok/s needs ≥67 GB/s · RTX 5090 ~1339, RTX 3090 Ti ~753
Which Hardware Can Run Qwen3.5 0.8B?
Q4_K_M · 0.9 GBQwen3.5 0.8B (Q4_K_M) requires 0.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 262K context window can add up to 1.6 GB, bringing total usage to 2.4 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Qwen3.5 0.8B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.1 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~568Simulate output on RTX 3080RTX 2080 Ti~460Simulate output on RTX 2080 TiRTX 3070 Ti~455Simulate output on RTX 3070 TiM3*8 GB~82Simulate output on iMac 24" M3 (8 GB)Orin Nano~76Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~55Simulate output on iPhone 1720 GB
fits · 19.1 GB free · up to 256K ctx
1 GPU
RX 7900 XT~552Simulate output on RX 7900 XT32–40 GB
fits · 31.1 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1339Simulate output on RTX 5090M5 Max36 GB~370Simulate output on Mac Studio M5 Max (36 GB)M532 GB~124Simulate output on MacBook Air 13" M5 (32 GB)Orin~153Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~101Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Qwen3.5 0.8B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
Alternatives to Qwen3.5 0.8B
Qwen 3.5 family · 34 models →Similar models
5| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| InternVL3 1BOpenGVLab | — | 2 GB | ~1057 | same size |
| InternVL2 1BOpenGVLab | — | 2 GB | ~1057 | same size |
| Bitnet B1.58 2B 4TMicrosoft | — | 2.3 GB | ~303 | same size |
| Gpt2 LargeOpenAI | — | 0.5 GB | ~1213 | same size |
| H2ovl Mississippi 800Mh2oai | — | 3.2 GB | ~360 | same size |
Specifications
- Publisher
- Alibaba
- Family
- Qwen 3.5
- Parameters
- 873M
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-02-28
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3.5 0.8B need?
Qwen3.5 0.8B requires 0.9 GB of VRAM at Q4_K_M, or 2.1 GB at BF16. Full 262K context adds up to 1.6 GB (2.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 873M × 4.8 bits ÷ 8 = 0.5 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 ≈ 1.9 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Qwen3.5 0.8B?
For Qwen3.5 0.8B, Q4_K_M (0.9 GB) offers the best balance of quality and VRAM usage. Q4_K_L (0.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.6 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3.5 0.8B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Qwen3.5 0.8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Qwen3.5 0.8B locally?
Yes — Qwen3.5 0.8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3.5 0.8B?
At Q4_K_M, Qwen3.5 0.8B can reach ~5517 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~753 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 ÷ 0.87 × 0.65 = ~5977 tok/s
Estimated speed at Q4_K_M (0.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3.5 0.8B?
At Q4_K_M, the download is about 0.52 GB. The full-precision BF16 version is 1.75 GB. The smallest option (IQ2_XXS) is 0.24 GB.
Which GPUs can run Qwen3.5 0.8B?
52 consumer GPUs can run Qwen3.5 0.8B 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 Qwen3.5 0.8B?
163 devices with unified memory can run Qwen3.5 0.8B at Q4_K_M (0.9 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.