Ryzen AI Max+ 395 128GB vs DGX Spark 128GB for local LLMs
Uses its largest memory option, 128 GB, with 8k context and an f16 KV cache.
What to know before choosing
Both machines come with 128GB of unified memory, but CanRun counts their GPU shares differently: about 70% on the Strix Halo, 89.6 GB, and on the DGX Spark what Linux and the desktop leave free, 116.9 GB, from public boot logs. gpt-oss-120b needs 64.3 GB and runs great on both, and Qwen3.5 122B-A10B runs well on both. The larger share shows with big low-bit files: the Q2_K file of Solar Open 2 250B runs slowly and CPU-only on the Strix Halo (theoretical) but runs well on the DGX Spark's GPU. Both also come with 64GB, the DGX Spark from NVIDIA's partner makers, and there gpt-oss-120b no longer loads.
Text generation follows memory bandwidth, which is close on these two. The dense Llama 3.3 70B fits fully but runs slowly on both, because every token reads all of its weights. The real difference is reading the prompt. With much more FP16 compute, CanRun expects the DGX Spark to cut the wait before the first token on long prompts, like pasted documents or coding-agent context. The summary's prompt-processing line gives a rough estimate (±40%).
Public benchmarks for gpt-oss-120b and Qwen3.5 122B-A10B on the two come from different builds and context lengths, so their gap says little about the hardware. Our 128GB guide covers a same-build run of both.
Speed
The Ryzen AI Max+ 395 128GB and the DGX Spark 128GB generate text at about the same speed (median of our estimates over the 55 models that fit entirely in memory on both at Q4_K_M or the closest available quant).
- Reference model
- Ling-3.0 Flash at Q4_K_M, the largest model that fits entirely in memory on both at Q4_K_M or the closest available quant
- Ryzen AI Max+ 395 128GB
- est. 48.4 tok/s (33.9–62.9, theoretical estimate ±30%)
- DGX Spark 128GB
- est. 52.8 tok/s (36.9–68.6, theoretical estimate ±30%)
- Prompt processing on Ling-3.0 Flash
- Ryzen AI Max+ 395 128GB: about 712 tok/s (427–997, rough estimate ±40%); DGX Spark 128GB: about 1,129 tok/s (678–1,581, rough estimate ±40%)
Specs side by side
| Spec | Ryzen AI Max+ 395 128GB | DGX Spark 128GB | Difference |
|---|---|---|---|
| Memory | 128 GB of unified memory | 128 GB of unified memory | Same |
| Memory bandwidth | 256.0 GB/s | 273.0 GB/s | 1.07× on the DGX Spark 128GB |
| FP16 compute | 29.7 TFLOPS | 62.5 TFLOPS | 2.1× on the DGX Spark 128GB |
| Launch year | 2025 | 2025 | — |
| Price | $1,999 launch MSRP (128 GB) | $3,999 launch MSRP (128 GB) | — |
| Public benchmark results | 17 results | 14 results | — |
Verdicts at a glance
Out of 58 models at Q4_K_M (or the closest available quant) with 8k context.
- Ryzen AI Max+ 395 128GBRuns great34 modelsRuns well12 modelsRuns slowly9 modelsWon't run3 models
- DGX Spark 128GBRuns great34 modelsRuns well12 modelsRuns slowly9 modelsWon't run3 models
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Where the verdicts differ
Every model gets the same verdict on both.
Every model on both
Scroll sideways to see every column.
| Model | Ryzen AI Max+ 395 128GB verdict | Ryzen AI Max+ 395 128GB speed | DGX Spark 128GB verdict | DGX Spark 128GB speed |
|---|---|---|---|---|
| Ling-3.0 FlashQ4_K_M | Runs great | est. 48.4 tok/s33.9–62.9theoretical estimate ±30% | Runs great | est. 52.8 tok/s36.9–68.6theoretical estimate ±30% |
| gpt-oss-120bMXFP4 | Runs great | 50.2 tok/s8k estimate 48.5 tok/s (38.8–58.1, calibrated estimate ±20%)measured (1 run, 512 context) | Runs great | 58.7 tok/s8k estimate 50.8 tok/s (40.6–60.9, calibrated estimate ±20%)measured (1 run, 2k context) |
| Kolibri 1Q4_K_M | Runs great | est. 48.0 tok/s38.4–57.6calibrated estimate ±20% | Runs great | est. 52.2 tok/s41.7–62.6calibrated estimate ±20% |
| K2-Horizon MoVA 36B-A4BQ4_K_M | Runs great | est. 35.1 tok/s24.5–45.6theoretical estimate ±30% | Runs great | est. 37.7 tok/s26.4–49.1theoretical estimate ±30% |
| Qwen3.5 35B-A3BQ4_K_M | Runs great | 64.8 tok/s8k estimate 56.0 tok/s (44.8–67.2, calibrated estimate ±20%)measured (1 run, 512 context) | Runs great | est. 61.9 tok/s49.5–74.2calibrated estimate ±20% |
| Qwen3.6 35B-A3BQ4_K_M | Runs great | 63.8 tok/s8k estimate 63.1 tok/s (50.5–75.7, calibrated estimate ±20%)measured (1 run, 512 context) | Runs great | est. 70.5 tok/s56.4–84.6calibrated estimate ±20% |
| MiniCPM-V 4.7 35B-A3BQ4_K_M | Runs great | est. 67.5 tok/s54.0–81.1calibrated estimate ±20% | Runs great | est. 76.0 tok/s60.8–91.2calibrated estimate ±20% |
| Nemotron 3.5 Lightning 30B-A3BQ4_K_M | Runs great | est. 65.9 tok/s46.1–85.7theoretical estimate ±30% | Runs great | est. 69.8 tok/s48.8–90.7theoretical estimate ±30% |
| Qwen3 30B-A3B (2507)Q4_K_M | Runs great | est. 54.2 tok/s43.3–65.0calibrated estimate ±20% | Runs great | est. 60.7 tok/s48.6–72.9calibrated estimate ±20% |
| Gemma 4 26B-A4BQ4_K_M | Runs great | 54.3 tok/s8k estimate 48.1 tok/s (38.5–57.7, calibrated estimate ±20%)measured (2 runs, 512 context) | Runs great | 47.0 tok/s8k estimate 51.5 tok/s (41.2–61.8, calibrated estimate ±20%)measured (1 run, 32k context) |
| gpt-oss-20bMXFP4 | Runs great | est. 68.6 tok/s54.8–82.3calibrated estimate ±20% | Runs great | est. 71.7 tok/s57.4–86.0calibrated estimate ±20% |
| Kanana 1.5 15.7B-A3BQ4_K_M | Runs great | est. 57.2 tok/s45.8–68.6calibrated estimate ±20% | Runs great | est. 62.2 tok/s49.7–74.6calibrated estimate ±20% |
| Gemma 3 12BQ4_K_M | Runs great | est. 26.8 tok/s21.4–32.1calibrated estimate ±20% | Runs great | est. 27.2 tok/s21.7–32.6calibrated estimate ±20% |
| Mellum2.1 12B-A2.5B ThinkingQ4_K_M | Runs great | est. 93.1 tok/s74.5–111.7calibrated estimate ±20% | Runs great | est. 104.4 tok/s83.5–125.2calibrated estimate ±20% |
| Qwen3.5 9BQ4_K_M | Runs great | 37.2 tok/s8k estimate 34.2 tok/s (27.4–41.0, calibrated estimate ±20%)measured (1 run, 4k context) | Runs great | 35.2 tok/s8k estimate 34.7 tok/s (27.8–41.6, calibrated estimate ±20%)measured (1 run, 4k context) |
| K2-Horizon 7BQ4_K_M | Runs great | est. 30.9 tok/s24.7–37.1calibrated estimate ±20% | Runs great | est. 31.3 tok/s25.1–37.6calibrated estimate ±20% |
| Qwen3 8BQ4_K_M | Runs great | 43.6 tok/s8k estimate 33.7 tok/s (26.9–40.4, calibrated estimate ±20%)measured (1 run, 512 context) | Runs great | 43.9 tok/s8k estimate 34.1 tok/s (27.3–41.0, calibrated estimate ±20%)measured (1 run, 512 context) |
| DeepSeek R1 0528 Qwen3 8BQ4_K_M | Runs great | est. 33.7 tok/s26.9–40.4calibrated estimate ±20% | Runs great | est. 34.1 tok/s27.3–41.0calibrated estimate ±20% |
| DeepSeek R1 Distill Llama 8BQ4_K_M | Runs great | est. 35.0 tok/s28.0–42.0calibrated estimate ±20% | Runs great | est. 35.5 tok/s28.4–42.6calibrated estimate ±20% |
| Kanana 1.5 8BQ4_K_M | Runs great | est. 35.0 tok/s28.0–42.0calibrated estimate ±20% | Runs great | est. 35.5 tok/s28.4–42.6calibrated estimate ±20% |
| Llama 3.1 8BQ4_K_M | Runs great | est. 35.0 tok/s28.0–42.0calibrated estimate ±20% | Runs great | est. 35.5 tok/s28.4–42.6calibrated estimate ±20% |
| Gemma 4 E4BQ4_K_M | Runs great | est. 59.3 tok/s41.5–77.1theoretical estimate ±30% | Runs great | est. 61.5 tok/s43.1–80.0theoretical estimate ±30% |
| Ling-3.0 TinyQ4_K_M | Runs great | est. 154.3 tok/s108.0–200.5theoretical estimate ±30% | Runs great | est. 179.8 tok/s125.8–233.7theoretical estimate ±30% |
| Gemma 4 E2BQ4_K_M | Runs great | est. 109.5 tok/s76.6–142.3theoretical estimate ±30% | Runs great | est. 115.9 tok/s81.1–150.6theoretical estimate ±30% |
| Qwen3.5 4BQ4_K_M | Runs great | est. 67.8 tok/s54.2–81.3calibrated estimate ±20% | Runs great | est. 68.7 tok/s55.0–82.5calibrated estimate ±20% |
| Nanbeige4.2 3BQ4_K_M | Runs great | est. 34.3 tok/s24.0–44.5theoretical estimate ±30% | Runs great | est. 34.8 tok/s24.3–45.2theoretical estimate ±30% |
| Spark-X2.5 4BQ4_K_M | Runs great | est. 72.3 tok/s57.9–86.8calibrated estimate ±20% | Runs great | est. 73.4 tok/s58.7–88.1calibrated estimate ±20% |
| Llama 3.2 3BQ4_K_M | Runs great | est. 70.9 tok/s56.7–85.1calibrated estimate ±20% | Runs great | est. 72.0 tok/s57.6–86.3calibrated estimate ±20% |
| LFM2.5 2.6BQ4_K_M | Runs great | est. 116.3 tok/s81.4–151.3theoretical estimate ±30% | Runs great | est. 118.0 tok/s82.6–153.4theoretical estimate ±30% |
| MiniCPM5 2BQ4_K_M | Runs great | est. 109.8 tok/s87.8–131.7calibrated estimate ±20% | Runs great | est. 111.4 tok/s89.1–133.6calibrated estimate ±20% |
| HyperCLOVA X SEED 1.5BQ4_K_M | Runs great | est. 115.6 tok/s92.5–138.8calibrated estimate ±20% | Runs great | est. 117.3 tok/s93.8–140.8calibrated estimate ±20% |
| EXAONE 4.0 1.2BQ4_K_M | Runs great | est. 159.8 tok/s127.9–191.8calibrated estimate ±20% | Runs great | est. 162.1 tok/s129.7–194.6calibrated estimate ±20% |
| Llama 3.2 1BQ4_K_M | Runs great | est. 194.7 tok/s155.7–233.6calibrated estimate ±20% | Runs great | est. 197.5 tok/s158.0–236.9calibrated estimate ±20% |
| MiniCPM5 1BQ4_K_M | Runs great | est. 235.5 tok/s188.4–282.6calibrated estimate ±20% | Runs great | est. 238.9 tok/s191.1–286.7calibrated estimate ±20% |
| Qwen3.5 122B-A10BQ4_K_M | Runs well | 20.9 tok/s8k estimate 22.7 tok/s (18.2–27.2, calibrated estimate ±20%)measured (1 run, 512 context) | Runs well | 29.0 tok/s8k estimate 24.0 tok/s (19.2–28.8, calibrated estimate ±20%)measured (1 run, 4k context) |
| Laguna S 2.1Q4_K_M | Runs well | est. 26.4 tok/s21.1–31.7calibrated estimate ±20% | Runs well | est. 28.4 tok/s22.7–34.1calibrated estimate ±20% |
| Solar Open 100BQ4_K_M | Runs well | est. 21.6 tok/s17.3–26.0calibrated estimate ±20% | Runs well | est. 22.8 tok/s18.3–27.4calibrated estimate ±20% |
| Muse Glimmer 30BQ4_K_M | Runs well | est. 12.1 tok/s9.6–14.5calibrated estimate ±20% | Runs well | est. 12.2 tok/s9.8–14.7calibrated estimate ±20% |
| Qwen3.6 27BQ4_K_M | Runs well | est. 12.1 tok/s9.7–14.5calibrated estimate ±20% | Runs well | est. 12.3 tok/s9.8–14.7calibrated estimate ±20% |
| Gemma 3 27BQ4_K_M | Runs well | est. 12.2 tok/s9.8–14.6calibrated estimate ±20% | Runs well | est. 12.4 tok/s9.9–14.8calibrated estimate ±20% |
| Mistral Small 3.2 24BQ4_K_M | Runs well | est. 13.4 tok/s10.7–16.1calibrated estimate ±20% | Runs well | est. 13.6 tok/s10.9–16.3calibrated estimate ±20% |
| Qwen3 14BQ4_K_M | Runs well | est. 20.3 tok/s16.2–24.4calibrated estimate ±20% | Runs well | est. 20.6 tok/s16.5–24.7calibrated estimate ±20% |
| DeepSeek R1 Distill Qwen 14BQ4_K_M | Runs well | est. 19.8 tok/s15.8–23.8calibrated estimate ±20% | Runs well | est. 20.1 tok/s16.1–24.1calibrated estimate ±20% |
| HyperCLOVA X SEED Think 14BQ4_K_M | Runs well | est. 20.6 tok/s14.4–26.8theoretical estimate ±30% | Runs well | est. 20.9 tok/s14.6–27.2theoretical estimate ±30% |
| Phi-4Q4_K_M | Runs well | est. 19.6 tok/s15.7–23.5calibrated estimate ±20% | Runs well | est. 19.8 tok/s15.9–23.8calibrated estimate ±20% |
| Gemma 4 12BQ4_K_M | Runs well | 24.4 tok/s8k estimate 28.9 tok/s (23.2–34.7, calibrated estimate ±20%)measured (1 run, 512 context) | Runs well | est. 29.4 tok/s23.5–35.2calibrated estimate ±20% |
| Llama 3.3 70BQ4_K_M | Runs slowly | est. 4.6 tok/s3.7–5.6calibrated estimate ±20% | Runs slowly | 4.7 tok/s8k estimate 4.7 tok/s (3.8–5.7, calibrated estimate ±20%)measured (2 runs, 512 context) |
| EXAONE 4.5 33BQ4_K_M | Runs slowly | est. 10.2 tok/s8.2–12.2calibrated estimate ±20% | Runs slowly | est. 10.3 tok/s8.3–12.4calibrated estimate ±20% |
| DeepSeek R1 Distill Qwen 32BQ4_K_M | Runs slowly | est. 9.5 tok/s7.6–11.5calibrated estimate ±20% | Runs slowly | est. 9.7 tok/s7.7–11.6calibrated estimate ±20% |
| Qwen3 32BQ4_K_M | Runs slowly | 10.2 tok/s8k estimate 9.6 tok/s (7.7–11.5, calibrated estimate ±20%)measured (2 runs, 512 context) | Runs slowly | 10.7 tok/s8k estimate 9.7 tok/s (7.8–11.7, calibrated estimate ±20%)measured (2 runs, 512 context) |
| EXAONE 4.0 32BQ4_K_M | Runs slowly | est. 10.6 tok/s8.4–12.7calibrated estimate ±20% | Runs slowly | est. 10.7 tok/s8.6–12.9calibrated estimate ±20% |
| Gemma 4 31BQ4_K_M | Runs slowly | est. 11.1 tok/s8.8–13.3calibrated estimate ±20% | Runs slowly | 10.1 tok/s8k estimate 11.2 tok/s (9.0–13.5, calibrated estimate ±20%)measured (1 run, 512 context) |
| Granite 4.2 30BQ4_K_M | Runs slowly | est. 10.6 tok/s8.5–12.7calibrated estimate ±20% | Runs slowly | est. 10.7 tok/s8.6–12.9calibrated estimate ±20% |
| Qwen3.5 27BQ4_K_M | Runs slowly | est. 11.9 tok/s9.5–14.3calibrated estimate ±20% | Runs slowly | 11.3 tok/s8k estimate 12.1 tok/s (9.7–14.5, calibrated estimate ±20%)measured (1 run, 4k context) |
| Qwen3.8 27BQ4_K_M | Runs slowly | est. 11.7 tok/s9.3–14.0calibrated estimate ±20% | Runs slowly | est. 11.8 tok/s9.5–14.2calibrated estimate ±20% |
| GLM-5.3 FlashQ4_K_M | Won't run | — | Won't run | — |
| DeepSeek V4 Flash 0731MXFP4 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 19.1 tok/s13.4–24.9theoretical estimate ±30% | Won't run | — |
| Solar Open 2 250BIQ4_XS | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 18.0 tok/s12.6–23.4theoretical estimate ±30% | Won't runTry Q2_K (heavy quality loss): Runs well | est. 22.0 tok/s17.6–26.3calibrated estimate ±20% |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Public benchmarks
Measured results on the Ryzen AI Max+ 395 128GB
| Model | Quant | Backend | Context | Prompt (tok/s) | Generation (tok/s) | Flags | Source | Measured |
|---|---|---|---|---|---|---|---|---|
| gpt-oss-120b | MXFP4 | llama.cpp | 512 | 707.0 | 50.2 | ROCm 7.0.2, no mmap | quozul.dev | 2025-10-27 |
| Gemma 4 26B-A4B | Q4_K_M | llama.cpp | 512 | 1,327.0 | 55.5 | Vulkan | github.com | 2026-06-30 |
| Gemma 4 26B-A4B | Q4_K_M | llama.cpp | 512 | 1,209.0 | 53.0 | Vulkan | github.com | 2026-08-18 |
| Gemma 4 26B-A4B | UD-Q4_K_XL | llama.cpp | 512 | 1,325.0 | 54.7 | Vulkan | github.com | 2026-05-18 |
| Gemma 4 31B | UD-Q4_K_XL | llama.cpp | 512 | 302.0 | 11.5 | Vulkan | github.com | 2026-05-18 |
| Gemma 4 12B | IQ4_XS | llama.cpp | 512 | 680.0 | 25.7 | Vulkan | github.com | 2026-06-04 |
| Gemma 4 12B | Q4_K_M | llama.cpp | 512 | 685.0 | 24.4 | Vulkan | github.com | 2026-06-04 |
| Qwen3.6 35B-A3B | Q8_0 | llama.cpp | 512 | — | 50.6 | Vulkan, FA off | github.com | 2026-06-10 |
| Qwen3.6 35B-A3B | UD-Q8_K_XL | llama.cpp | 512 | 1,046.0 | 46.2 | Vulkan | github.com | 2026-04-26 |
| Qwen3.6 35B-A3B | Q4_K_M | llama.cpp | 512 | 1,064.0 | 63.8 | Vulkan | github.com | 2026-04-26 |
| Qwen3.5 35B-A3B | Q4_K_M | llama.cpp | 512 | 1,077.0 | 64.8 | Vulkan | github.com | 2026-04-26 |
| Qwen3.5 9B | Q4_K_M | llama.cpp | 4k | 969.0 | 37.2 | Vulkan | localmaxxing.com | 2026-04-26 |
| Qwen3.5 122B-A10B | Q4_K_M | llama.cpp | 512 | 315.0 | 20.9 | KV q8_0 | github.com | 2026-07-19 |
| Qwen3 8B | Q4_K_M | llama.cpp | 512 | 1,238.0 | 43.6 | Vulkan | github.com | 2026-09-08 |
| Qwen3 32B | Q4_K_M | llama.cpp | 512 | 256.0 | 9.9 | ROCm | blog.tosukui.xyz | 2025-07-13 |
| Qwen3 32B | Q4_K_M | llama.cpp | 512 | 140.0 | 10.4 | Vulkan | blog.tosukui.xyz | 2025-05-16 |
| Qwen3 32B | Q8_0 | llama.cpp | 512 | 77.0 | 6.4 | ROCm | llm-tracker.info | 2025-05-11 |
Measured results on the DGX Spark 128GB
| Model | Quant | Backend | Context | Prompt (tok/s) | Generation (tok/s) | Flags | Source | Measured |
|---|---|---|---|---|---|---|---|---|
| gpt-oss-120b | MXFP4 | llama.cpp | 2k | 2,444.0 | 58.7 | CUDA, no mmap | github.com | 2026-02-05 |
| Gemma 4 31B | Q4_K_M | llama.cpp | 512 | 687.0 | 10.1 | CUDA | github.com | 2026-04-14 |
| Gemma 4 26B-A4B | Q4_K_M | llama.cpp | 32k | — | 47.0 | CUDA, depth 32768 | github.com | 2026-06-11 |
| Qwen3.5 35B-A3B | Q8_0 | llama.cpp | 2k | 2,572.0 | 49.2 | CUDA | github.com | 2026-03-12 |
| Qwen3.5 9B | Q4_K_M | llama.cpp | 4k | — | 35.2 | — | github.com | 2026-08-13 |
| Qwen3.5 27B | Q4_K_M | llama.cpp | 4k | — | 11.3 | — | github.com | 2026-08-13 |
| Qwen3.5 122B-A10B | Q4_K_M | llama.cpp | 4k | — | 29.0 | — | github.com | 2026-08-13 |
| Llama 3.3 70B | Q4_K_M | llama.cpp | 512 | 284.0 | 4.7 | CUDA, Vulkan | github.com | 2025-11-22 |
| Llama 3.3 70B | Q4_K_M | llama.cpp | 512 | — | 4.6 | CUDA | github.com | 2026-08-12 |
| Llama 3.3 70B | Q8_0 | llama.cpp | 512 | — | 2.9 | CUDA | github.com | 2026-08-12 |
| Llama 3.3 70B | Q2_K | llama.cpp | 512 | — | 7.2 | CUDA | github.com | 2026-08-12 |
| Qwen3 32B | Q4_K_M | llama.cpp | 512 | 630.0 | 10.5 | CUDA, Vulkan | github.com | 2025-11-22 |
| Qwen3 32B | Q4_K_M | llama.cpp | 512 | 762.0 | 10.8 | CUDA | github.com | 2025-12-05 |
| Qwen3 8B | Q4_K_M | llama.cpp | 512 | 3,168.0 | 43.9 | CUDA | github.com | 2025-12-05 |
Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.
Frequently asked questions
Which is faster for local LLMs, the Ryzen AI Max+ 395 128GB or the DGX Spark 128GB?
The Ryzen AI Max+ 395 128GB and the DGX Spark 128GB generate text at about the same speed (median of our estimates over the 55 models that fit entirely in memory on both at Q4_K_M or the closest available quant). Estimated speed on Ling-3.0 Flash at Q4_K_M: the Ryzen AI Max+ 395 128GB est. 48.4 tok/s (33.9–62.9, theoretical estimate ±30%); the DGX Spark 128GB est. 52.8 tok/s (36.9–68.6, theoretical estimate ±30%).
What is the largest model each can run entirely in memory?
The Ryzen AI Max+ 395 128GB fits Ling-3.0 Flash at Q4_K_M (77.01 GB file) entirely in 128 GB of unified memory, at est. 48.4 tok/s (33.9–62.9, theoretical estimate ±30%). The DGX Spark 128GB fits Ling-3.0 Flash at Q4_K_M (77.01 GB file) entirely in 128 GB of unified memory, at est. 52.8 tok/s (36.9–68.6, theoretical estimate ±30%).
How many local LLMs run well on each?
At Q4_K_M with 8k context, out of 58 tracked models: the Ryzen AI Max+ 395 128GB — 34 Runs great, 12 Runs well, 9 Runs slowly, 3 Won't run; the DGX Spark 128GB — 34 Runs great, 12 Runs well, 9 Runs slowly, 3 Won't run. Every model gets the same verdict on both.
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.