Yes — with 94.8 GB to spare
Qwen3.5 0.8B at Q4_K_M fits your DGX Spark · 128 GB entirely in unified memory at 8K context, at an estimated 312 tokens per second. There is room for its full 256K window.
Draft model for speculative decoding, or a classifier that fits in 1 GB.
Hardware requirements What hardware do I need to run Qwen3.5 0.8B? →At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 1.6 GB | 2.3 GB | 256K | 94 | Reference | Long context |
| Q8_0 | 0.9 GB | 1.6 GB | 256K | 177 | −0.1% ppl | Long context |
| Q6_K | 0.7 GB | 1.4 GB | 256K | 230 | −0.4% ppl | Long context |
| Q5_K_M | 0.6 GB | 1.3 GB | 256K | 266 | −0.8% ppl | Long context |
| Q4_K_M | 0.5 GB | 1.2 GB | 256K | 312 | −1.9% ppl | Recommended |
| Q3_K_M | 0.4 GB | 1.1 GB | 256K | 385 | −5.4% ppl | Long context |
| Q2_K | 0.3 GB | 1.0 GB | 256K | 450 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 6 of its 24 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.
How to run it
$ ollama pull qwen3.5:0.8b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen3.5:0.8b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on a DGX Spark · 128 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3.5 2B 2.27B · same family |
Q4_K_M · 2.0 GB | 120 | Runs great |
| Qwen3.5 4B 4.66B · same family |
Q4_K_M · 3.5 GB | 58 | Runs great |
| Qwen3.5 9B 9.65B · same family |
Q4_K_M · 6.3 GB | 28 | Runs great |
| Qwen3.5 122B-A10B 125B MoE · same family |
Q4_K_M · 71.1 GB | 13 | Runs great |
| Gemma 3 1B 1.0B · similar size |
Q4_K_M · 1.2 GB | 271 | Runs great |
| Llama 3.2 1B Instruct 1.24B · similar size |
Q4_K_M · 1.5 GB | 219 | Runs great |
| Qwen3 0.6B 0.6B · similar size |
Q4_K_M · 1.8 GB | 452 | Runs great |
Qwen3.5 0.8B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 3060 Laptop 5.3 GB usable · 336 GB/s |
1.2 GB | 416 | Runs great |
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
1.2 GB | 317 | Runs great |
| M3 · 8 GB 5.4 GB usable · 100 GB/s |
1.2 GB | 114 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
1.2 GB | 445 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
1.2 GB | 137 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
1.2 GB | 1247 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
1.2 GB | 1188 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
1.2 GB | 457 | Runs great |