Skip to content
Local AI Wizard
Your machine
Theme

NVIDIA DGX Spark vs Framework Desktop 128 GB

DGX Spark · 128 GB unified and Framework Desktop · Ryzen AI Max+ 395 · 128 GB side by side for local AI.

Facts from both hardware pages

NVIDIA DGX Spark vs Framework Desktop 128 GB: memory, bandwidth, models and prices
SpecificationNVIDIA DGX SparkFramework Desktop 128 GB
Memory128 GB unified memoryShared by CPU and GPU · source128 GB unified memoryShared by CPU and GPU · source
Memory bandwidth273 GB/sManufacturer spec · not model speed · source256 GB/sManufacturer spec · not model speed · source
Text · run well849+1 tight fit · within 128 GB849+1 tight fit · within 128 GB
Vision · run well1,103within 128 GB1,103within 128 GB
Image · within memory174within 128 GB · documented paths and minimums174within 128 GB · documented paths and minimums
Video · within memory132within 128 GB · documented paths and minimums132within 128 GB · documented paths and minimums
Audio · within memory389within 128 GB · documented paths and minimums389within 128 GB · documented paths and minimums
Embeddings · within memory654within 128 GB · 8-bit estimate654within 128 GB · 8-bit estimate
Published speed runs1413 on this machine · 1 naming only the chip44 on this machine
Launch price (MSRP)USD 3,999US · dated 2025-10-15 · not a tracked offer · sourceUSD 1,999US · dated 2025-02-25 · not a tracked offer · source
Where to buyNVIDIA Marketplacethis configuration · US · recorded 2026-10-18 · store linkNo manufacturer store link on file

Counts use the same memory estimate as each hardware page: text and vision run well within the fast memory (tight fits counted apart); image, video and audio use documented paths and publisher minimums. Formulas

Top text models each runs well

The first 5 rows of each hardware page's Text list, in its order: LiveBench score, then reviewed models, then Hub downloads. Memory is the planning estimate on that machine.

NVIDIA DGX Spark vs Framework Desktop 128 GB: top text models that run well
RankNVIDIA DGX SparkFramework Desktop 128 GB
#1Smaug MiniAbacus AI · LiveBench 76.9 · ~29 GBSmaug MiniAbacus AI · LiveBench 76.9 · ~29 GB
#2Qwen3.8 27BAlibaba · LiveBench 75.3 · ~29 GBQwen3.8 27BAlibaba · LiveBench 75.3 · ~29 GB
#3Qwen3.6 27BAlibaba · LiveBench 64 · ~29 GBQwen3.6 27BAlibaba · LiveBench 64 · ~29 GB
#4Nemotron 3.5 Lightning 30B A3BNVIDIA · LiveBench 44.5 · ~31 GBNemotron 3.5 Lightning 30B A3BNVIDIA · LiveBench 44.5 · ~31 GB
#5Qwen3 14BAlibaba · ~20 GBQwen3 14BAlibaba · ~20 GB

Measured speed

Published output tokens per second, as measured. A speed is compared only when the same checkpoint, quantization, runtime and lengths ran on both machines themselves; same-chip references are not compared.

No published test ran the same model and settings on both machines.

All published measurements · NVIDIA DGX Spark13 on this machine · 1 naming only the chip
Published measurements on this hardware
gpt-oss 20B MXFP4 MoEggml-org/gpt-oss-20b-GGUFDGX Spark · 1× NVIDIA GB1083.43 ± 0.59MXFP4 MoE
0 / 32 · Not reported by llama-bench
CUDA
llama.cpp 11fb327bf (7941); CUDA
Flash Attention enabled
llama.cpp bench
2026-09-25
gemma-3-4b-it-qat Q4_0ggml-org/gemma-3-4b-it-qat-GGUF · llama-ben…DGX Spark · 1× NVIDIA GB1081.05 ± 0.20Q4_0
0 / 32 · Single llama-bench process;…
llama.cpp CUDA
llama.cpp commit 11fb327bf
Flash Attention enabled
llama.cpp benches/dgx-spark · maintainer result
2026-10-25
Qwen3.5 35B A3B MXFP4Qwen3.5-35B-A3B MXFP4 GGUF (the source name…DGX Spark · 1× NVIDIA GB10 · 128 GB unified63.13MXFP4 (MoE; 35B total / 3B active)
0 / 128 · Single llama-bench process;…
llama.cpp CUDA (SM121a, source build)
llama.cpp b8922 (commit 13d36cf89); cma…
Flash Attention enabled
nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark
2026-10-09
Qwen3 Coder 30B A3B Q8_0ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-…DGX Spark · 1× NVIDIA GB1061.06 ± 0.23Q8_0
0 / 32 · Not reported by llama-bench
CUDA
llama.cpp 11fb327bf (7941); CUDA
Flash Attention enabled
llama.cpp bench
2026-09-25
Llama 2 7B Q4_0Llama 2 7B Q4_0 (scoreboard model; the scor…Nvidia GB10 · 128 GB (memory size not stated by the source; this chip is sold with one memory size) · coopmat260.39 ± 0.05Q4_0
0 / 128 · Single llama-bench process;…
Vulkan
llama.cpp commit 657e011
Flash Attention enabled
llama.cpp Vulkan scoreboard · community result
2026-10-25
gpt-oss-120b MXFP4 MoEggml-org/gpt-oss-120b-GGUF · llama-bench mo…DGX Spark · 1× NVIDIA GB1058.72 ± 0.20MXFP4 MoE
0 / 32 · Single llama-bench process;…
llama.cpp CUDA
llama.cpp commit 11fb327bf
Flash Attention enabled
llama.cpp benches/dgx-spark · maintainer result
2026-10-25
Nemotron-3-Nano-4B Q8_0ggml-org/Nemotron-3-Nano-4B-GGUF · llama-be…DGX Spark · 1× NVIDIA GB1052.85 ± 0.12Q8_0
0 / 32 · Single llama-bench process;…
llama.cpp CUDA
llama.cpp commit 1bbec6a75
Flash Attention enabled
llama.cpp benches/nemotron · maintainer result
2026-10-25
GLM-4.7-Flash Q8_0ggml-org/GLM-4.7-Flash-GGUF · llama-bench m…DGX Spark · 1× NVIDIA GB1048.68 ± 0.12Q8_0
0 / 32 · Single llama-bench process;…
llama.cpp CUDA
llama.cpp commit 11fb327bf
Flash Attention enabled
llama.cpp benches/dgx-spark · maintainer result
2026-10-25
Qwen3.8 27B NVFP4 + DSparkRadixArk/Qwen3.8-27B-NVFP4DGX Spark · 1× GB1036.6NVFP4 + DSpark
128 / 128 · C1
SGLang
sparkrun v0.3.4; lmsysorg/sglang@sha256…
NVIDIA Developer Forum
2026-09-25
Qwen2.5-Coder-7B-Q8_0ggml-org/Qwen2.5-Coder-7B-Q8_0-GGUF · llama…DGX Spark · 1× NVIDIA GB1029.43 ± 0.02Q8_0
0 / 32 · Single llama-bench process;…
llama.cpp CUDA
llama.cpp commit 11fb327bf
Flash Attention enabled
llama.cpp benches/dgx-spark · maintainer result
2026-10-25
Nemotron 3 Super 120B A12B Q4_Kggml-org/Nemotron-3-Super-120B-GGUF · Q4_K …DGX Spark · 1× NVIDIA GB10 · 128 GB unified19.94 ± 0.16Q4_K (reported as 'Q4_K' by llama-bench; GGUF from ggml-org)
0 / 32 · Single llama-bench process;…
llama.cpp CUDA
llama.cpp build 04a65daab (8268); n_uba…
Flash Attention enabled
llama.cpp benches/nemotron · DGX Spark
2026-10-09
Qwen3.8 27B NVFP4 + MTPInferact/Qwen3.8-27B-NVFP4DGX Spark · 1× GB1018.5NVFP4 + MTP (3 speculative tokens)
128 / 128 · C1
vLLM official
sparkrun v0.3.4; vllm/vllm-openai:qwen3…
NVIDIA Developer Forum
2026-09-25
Qwen3.6 27B Q4_K_MQwen3.6-27B Q4_K_M GGUF, 15.65 GiB (Unsloth…DGX Spark · 1× NVIDIA GB10 · 128 GB unified11.85 ± 0.01Q4_K_M (15.65 GiB)
0 / 128 · Single llama-bench process;…
llama.cpp CUDA (SM121a, source build)
llama.cpp b8922 (commit 13d36cf89); cma…
Flash Attention enabled
nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark
2026-10-09
Qwen3.6 27B BF16Qwen3.6-27B BF16 GGUF, 50.10 GiB (Unsloth b…DGX Spark · 1× NVIDIA GB10 · 128 GB unified4.54 ± 0.00BF16 (50.10 GiB)
0 / 128 · Single llama-bench process;…
llama.cpp CUDA (SM121a, source build)
llama.cpp b8922 (commit 13d36cf89); cma…
Flash Attention enabled
nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark
2026-10-09
All published measurements · Framework Desktop 128 GB4 on this machine
Published measurements on this hardware
Nemotron 3 Super 120B A12B UD-Q4_K_XLNVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_X…Framework Desktop · AMD Ryzen AI Max+ 395 (Radeon 8060S) · 128 GB unified14.86 ± 0.06UD-Q4_K_XL (llama-bench: Q4_K - Medium, 78.02 GiB)
0 / 128 · Single llama-bench process;…
llama.cpp Vulkan (Mesa RADV, toolbox vulkan_radv)
llama.cpp build 1a68ec937 (9193); -ngl …
Flash Attention enabled
kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark
2026-10-09
Nemotron 3 Super 120B A12B UD-Q4_K_XLNVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_X…Framework Desktop · AMD Ryzen AI Max+ 395 (Radeon 8060S) · 128 GB unified14.85 ± 0.04UD-Q4_K_XL (llama-bench: Q4_K - Medium, 78.02 GiB)
0 / 128 · Single llama-bench process;…
llama.cpp ROCm 7.2.3 (toolbox rocm-7.2.3)
llama.cpp build 1a68ec937 (9193); -ngl …
Flash Attention enabled
kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark
2026-10-09
Qwen3.6 27B UD-Q8_K_XLQwen3.6-27B-UD-Q8_K_XL.gguf (Unsloth UD-Q8_…Framework Desktop · AMD Ryzen AI Max+ 395 (Radeon 8060S) · 128 GB unified6.51 ± 0.00UD-Q8_K_XL (llama-bench: Q8_0, 33.31 GiB)
0 / 128 · Single llama-bench process;…
llama.cpp ROCm 7.2.3 (toolbox rocm-7.2.3)
llama.cpp build 1a68ec937 (9193); -ngl …
Flash Attention enabled
kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark
2026-10-09
Qwen3.6 27B UD-Q8_K_XLQwen3.6-27B-UD-Q8_K_XL.gguf (Unsloth UD-Q8_…Framework Desktop · AMD Ryzen AI Max+ 395 (Radeon 8060S) · 128 GB unified6.30 ± 0.00UD-Q8_K_XL (llama-bench: Q8_0, 33.31 GiB)
0 / 128 · Single llama-bench process;…
llama.cpp Vulkan (Mesa RADV, toolbox vulkan_radv)
llama.cpp build 1a68ec937 (9193); -ngl …
Flash Attention enabled
kyuz0/amd-strix-halo-toolboxes raw llama-bench log (GitHub) · community benchmark
2026-10-09

Verdict

Both have 128 GB unified memory. By the memory estimate, 849 text models run well on each. NVIDIA DGX Spark lists 273 GB/s of memory bandwidth, 1.1× the 256 GB/s of Framework Desktop 128 GB (a manufacturer spec, not a measured speed). No published test ran the same model and settings on both, so their speeds are not compared here. Launch prices on file: NVIDIA DGX Spark USD 3,999 (2025-10-15) and Framework Desktop 128 GB USD 1,999 (2025-02-25). On these facts neither leads: the same number of text models run well and no shared measurement compares their speed.

Limits and dates

Model counts are memory estimates, not speed measurements or guaranteed fits; verify runtime and checkpoint support. Bandwidth is the manufacturer's figure. Prices are launch or list prices with their dates, not current offers.

Page updated · Model catalog checked · LiveBench 2026-06-25