Which local LLMs fit on a DGX Spark GB10 (128 GB unified)?
The DGX Spark (GB10) has 128 GB LPDDR5x coherent unified system memory, shared by the CPU and GPU. After a 16 GiB reserve for the system, about 112 GiB is left for a model. At an 8K context the largest model in our list that fits is gpt-oss-120b at MXFP4 (about 62.8 GiB). Qwen3.8-Flash-Next at Q4_K_M is tight (about 111.8 GiB–131.5 GiB).
These are estimates from the model's config and file sizes, not measurements. How we calculate
Which models fit at 8K
Each model uses the highest-precision file that fits, one chat at a time.
Fits (65)
| Model | Quant | Total |
|---|---|---|
| GLM-4.5-Air | GGUF Q6_K (Unsloth) | 93.8 GiB–96.1 GiB |
| Qwen3-Next-80B-A3B-Instruct | GGUF Q8_0 (Qwen) | 79.9 GiB–81.9 GiB |
| Qwen2.5-72B-Instruct | GGUF Q8_0 (Qwen) | 74.8 GiB–76.8 GiB |
| Llama-3.1-Nemotron-70B-Instruct-HF | GGUF Q8_0 (bartowski) | 72.5 GiB–74.4 GiB |
| gpt-oss-120b | MXFP4 safetensors | 61.2 GiB–62.8 GiB |
| Mixtral-8x7B-Instruct-v0.1 | GGUF Q8_0 (mradermacher) | 47.3 GiB–48.7 GiB |
| Qwen2.5-32B-Instruct | GGUF Q8_0 (Qwen) | 34.6 GiB–35.7 GiB |
| Qwen2.5-VL-32B-Instruct | GGUF Q8_0 (mradermacher) | 34.6 GiB–35.7 GiB |
| Qwen2.5-Coder-32B-Instruct | GGUF Q8_0 (Qwen) | 34.6 GiB–35.7 GiB |
| QwQ-32B | GGUF Q8_0 (Qwen) | 34.6 GiB–35.7 GiB |
| DeepSeek-R1-Distill-Qwen-32B | GGUF Q8_0 (Unsloth) | 34.6 GiB–35.7 GiB |
| OpenMath-Nemotron-32B | GGUF Q8_0 (mradermacher) | 34.6 GiB–35.7 GiB |
| Qwen3-32B | GGUF Q8_0 (Qwen) | 34.6 GiB–35.7 GiB |
| Qwen3.8-27B | GGUF Q8_0 (Unsloth) | 27.8 GiB–33.1 GiB |
| Qwen3-VL-30B-A3B-Instruct | GGUF Q8_0 (Qwen) | 31.1 GiB–32.2 GiB |
| Qwen3-30B-A3B-Instruct-2507 | GGUF Q8_0 (Unsloth) | 31.1 GiB–32.2 GiB |
| Qwen3-30B-A3B | GGUF Q8_0 | 31.1 GiB–32.2 GiB |
| Drama 3 | Unofficial int4 W4A16 (GPTQ-Marlin, with codec) | 22.7 GiB–27.0 GiB |
| Mistral-Small-24B-Instruct-2501 | GGUF Q8_0 (Unsloth) | 24.7 GiB–25.6 GiB |
| DeepSeek-V2-Lite-Chat | GGUF Q8_0 (mradermacher) | 15.9 GiB–19.2 GiB |
| Gemma 3 27B IT | GGUF Q4_0 (Google QAT) | 17.2 GiB–18.0 GiB |
| Qwen2.5-14B-Instruct | GGUF Q8_0 | 16.2 GiB–17.0 GiB |
| Qwen2.5-Coder-14B-Instruct | GGUF Q8_0 (Qwen) | 16.2 GiB–17.0 GiB |
| OpenMath-Nemotron-14B | GGUF Q8_0 (mradermacher) | 16.2 GiB–17.0 GiB |
| Phi-4-reasoning | GGUF Q8_0 (Unsloth) | 16.2 GiB–17.0 GiB |
| phi-4 | GGUF Q8_0 (Microsoft) | 16.2 GiB–17.0 GiB |
| Llama 3.1 8B Instruct | Official BF16 safetensors | 16.1 GiB–16.8 GiB |
| Qwen3-14B | GGUF Q8_0 (Qwen) | 16.0 GiB–16.8 GiB |
| Mistral-Nemo-Instruct-2407 | GGUF Q8_0 (Unsloth) | 13.5 GiB–14.2 GiB |
| gpt-oss-20b | MXFP4 safetensors | 13.1 GiB–13.8 GiB |
| GLM-4-9B-0414 | GGUF Q8_0 (Unsloth) | 9.8 GiB–10.3 GiB |
| granite-3.3-8b-instruct | GGUF Q8_0 (IBM) | 9.5 GiB–10.1 GiB |
| Qwen3-VL-8B-Instruct | GGUF Q8_0 (Qwen) | 9.4 GiB–10.0 GiB |
| Qwen3-8B-Base | GGUF Q8_0 (mradermacher) | 9.4 GiB–10.0 GiB |
| Qwen3-8B | GGUF Q8_0 | 9.4 GiB–10.0 GiB |
| Qwen2.5-Math-7B-Instruct | GGUF Q8_0 (bartowski) | 8.1 GiB–10.0 GiB |
| DeepSeek-R1-Distill-Llama-8B | GGUF Q8_0 (Unsloth) | 9.1 GiB–9.7 GiB |
| Gemma 3 12B IT | GGUF Q4_0 (Google QAT) | 8.5 GiB–9.0 GiB |
| Mistral-7B-Instruct-v0.3 | GGUF Q8_0 (bartowski) | 8.3 GiB–8.9 GiB |
| Qwen2.5-Coder-7B | GGUF Q8_0 (mradermacher) | 8.1 GiB–8.7 GiB |
| Qwen2.5-Coder-7B-Instruct | GGUF Q8_0 (Qwen) | 8.1 GiB–8.7 GiB |
| Qwen2.5-7B-Instruct | GGUF Q8_0 | 8.1 GiB–8.7 GiB |
| DeepSeek-R1-Distill-Qwen-7B | GGUF Q8_0 (Unsloth) | 8.1 GiB–8.7 GiB |
| OpenMath-Nemotron-7B | GGUF Q8_0 (mradermacher) | 8.1 GiB–8.7 GiB |
| Qwen2.5-VL-7B-Instruct | GGUF Q8_0 (Unsloth) | 8.1 GiB–8.7 GiB |
| Qwen2-7B-Instruct | GGUF Q8_0 (Qwen) | 8.1 GiB–8.7 GiB |
| Phi-3.5-mini-instruct | GGUF Q8_0 (bartowski) | 6.9 GiB–7.6 GiB |
| Llama 3.2 3B Instruct | Official BF16 safetensors | 7.0 GiB–7.5 GiB |
| Qwen3-VL-4B-Instruct | GGUF Q8_0 (Qwen) | 5.2 GiB–5.8 GiB |
| Qwen3-4B-Instruct-2507 | GGUF Q8_0 (Unsloth) | 5.2 GiB–5.8 GiB |
| Qwen3-4B | GGUF Q8_0 | 5.2 GiB–5.8 GiB |
| Phi-4-mini-instruct | GGUF Q8_0 (Unsloth) | 4.9 GiB–5.5 GiB |
| Qwen2.5-Coder-3B-Instruct | GGUF Q8_0 (Qwen) | 3.8 GiB–4.2 GiB |
| Qwen2.5-3B-Instruct | GGUF Q8_0 | 3.8 GiB–4.2 GiB |
| Qwen2.5-VL-3B-Instruct | GGUF Q8_0 (Unsloth) | 3.5 GiB–3.9 GiB |
| SmolLM2-1.7B-Instruct | GGUF Q8_0 (Unsloth) | 3.3 GiB–3.8 GiB |
| Gemma 3 4B IT | GGUF Q4_0 (Google QAT) | 3.3 GiB–3.8 GiB |
| Qwen3-1.7B-Base | GGUF Q8_0 (mradermacher) | 2.7 GiB–3.2 GiB |
| Qwen3-1.7B | GGUF Q8_0 | 2.7 GiB–3.2 GiB |
| Llama 3.2 1B Instruct | Official BF16 safetensors | 2.7 GiB–3.1 GiB |
| Qwen2.5-Coder-1.5B-Instruct | GGUF Q8_0 (Qwen) | 2.1 GiB–2.5 GiB |
| Qwen2.5-1.5B-Instruct | GGUF Q8_0 (Qwen) | 2.1 GiB–2.5 GiB |
| Qwen3-0.6B | GGUF Q8_0 (Qwen) | 1.6 GiB–2.0 GiB |
| Gemma 3 1B IT | GGUF Q4_0 (Google QAT) | 1.1 GiB–1.5 GiB |
| Qwen2.5-0.5B-Instruct | GGUF Q8_0 (Qwen) | 0.8 GiB–1.2 GiB |
Tight fit (1)
| Model | Quant | Total |
|---|---|---|
| Qwen3.8-Flash-Next | GGUF Q4_K_M (bartowski) | 111.8 GiB–131.5 GiB |
Won't fit (20)
- MiniMax-M2 · Q4_K_M · 134 GiB
- Qwen3-235B-A22B · Q4_K_M · 137.1 GiB
- Qwen3-235B-A22B-Instruct-2507 · Q4_K_M · 137.1 GiB
- Llama 3.3 70B Instruct · BF16 · 137.2 GiB
- DeepSeek-V4-Flash-0731 · FP8 · 183.7 GiB
- GLM-4.6 · Q4_K_M · 208.4 GiB
- GLM-4.5 · Q4_K_M · 209.2 GiB
- MiniMax-M3 · Q4_K_M · 249.7 GiB
- GLM-5.3-Flash · Q8_0 · 373.6 GiB
- DeepSeek-V3 · Q4_K_M · 443.1 GiB
- DeepSeek-R1 · Q4_K_M · 443.1 GiB
- DeepSeek-V3-0324 · Q4_K_M · 443.1 GiB
- DeepSeek-R1-0528 · Q4_K_M · 443.7 GiB
- DeepSeek-V3.1 · Q4_K_M · 444.2 GiB
- Muse Spark Open · NVFP4 · 508.9 GiB
- DeepSeek-V4.1-Flash · FP8 · 558.8 GiB
- Ling-3.1-flash · FP8 · 628.3 GiB
- Kimi-K2-Instruct · Q4_K_M · 679.5 GiB
- Kimi-K2-Thinking · Q4_K_M · 680 GiB
- GLM-5.3 · Q8_0 · 877 GiB
Detailed checks
Known deployments on this hardware
4 known setupsReal deployment setups tested by maintainers and community labs on this hardware platform.
DeepSeek-V4.1-Flash
2× NVIDIA DGX Spark (GB10, 128 GB unified)
Quant:EXL3 2.9 bpw (mul1)(2.9 bpw)
Runtime:vLLM· TP2
Offload:Engram n-gram tables (shards 47+48) → NVME
Tested:
- ✓ generation
- ✓ 262,144 context
- ✓ tool calling
- ✓ vision
- ✓ speculative decoding
Measured:31.6 tok/s· 1 stream
2-node DGX Spark setup serving DeepSeek-V4.1-Flash with vLLM tensor-parallel size 2 over ConnectX-7 RoCE, EXL3 2.9 bpw mul1 weights, and native NVMe-resident Engram tables.
DeepSeek-V4.1-Flash
3× NVIDIA DGX Spark (GB10, 128 GB unified)
Quant:Native MXFP4 MoE + FP8 Dense
Runtime:SGLang· TP3
Offload:Engram n-gram tables (189 GiB) → NVME
Tested:
- ✓ generation
- ✓ ~208K Tested (256K cfg)
- ✓ tool calling
- ✓ vision
- ✓ speculative decoding
Measured:37.9 tok/s· 1 stream
3-node DGX Spark cluster running native MXFP4 experts and FP8 dense weights with SGLang TP=3 over ConnectX-7 RoCE triangle, with NVMe-resident Engram tables.
DeepSeek-V4.1-Flash
4× NVIDIA DGX Spark (GB10, 128 GB unified)
Quant:Native MXFP4 MoE + FP8 Dense (TP=4)
Runtime:SGLang· TP4
Offload:Engram n-gram tables (189 GiB) → NVME
Tested:
- ✓ generation
- ✓ 1,048,576 context
- ✓ tool calling
- ✓ vision
- ✓ speculative decoding
Measured:45.4 tok/s· 1 stream
4-node DGX Spark cluster running native MXFP4 MoE and FP8 dense weights with SGLang TP=4, verified 1M context needle test, and 8M pinned KV token pool.
DeepSeek-V4-Flash-0731
2× NVIDIA DGX Spark (GB10, 128 GB unified)
Quant:Official FP8 Safetensors
Runtime:vLLM· TP2
Tested:
- ✓ generation
- ✓ 1,048,576 context
- ✓ tool calling
- ✓ vision
- ✓ speculative decoding
Measured:75.4 tok/s· 1 stream
2-node DGX Spark deployment for DeepSeek-V4-Flash-Vision-Exp running vLLM TP=2 with DSpark speculative decoding and nvfp4_ds_mla KV cache.
Memory
- NVIDIANVIDIA DGX Spark 940-54242-0000
- Memory kindUnified memory
- Marketed128 GB LPDDR5x coherent unified system memory
- Gross128.00 GiB (137,438,953,472 bytes)
- Default reserve16.00 GiB (17,179,869,184 bytes)
- Net budget112.00 GiB (120,259,084,288 bytes)
The reserve is an adjustable assumption. On a headless machine you can lower it in the calculator.
Unified memory is one shared pool. System RAM is not added on top, and several machines are not one pool.
Related pages
Sources
- NVIDIA DGX Spark product page — 128 GB LPDDR5x coherent unified system memory. This is not dedicated VRAM. Default reserve deducts OS and other processes. Multiple Sparks are not one pool.
- NVIDIA DGX Spark hardware docs — 128 GB LPDDR5x unified memory on the GB10 Superchip.
Calculator
Loading catalog snapshot…
Pick a GPU or Mac to see which models fit, or pick a model to see how much memory it needs.
Pick a GPU to see which models fit.