UDOO BOLT V8

Hardware · AMD

What AI models can the UDOO BOLT V8 (32 GB) run?

Unified memory
32.0 GB
Usable for models
16.0 GB
Memory bandwidth
38 GB/s
Runs models on
GPU (Vulkan)
Released
2019
455 / 621 LLMs run Best: Gemma 4 26B-A4B 55 / 61 Image models run Best: FLUX.2 [klein] 4B 17 / 43 Video models run Best: LTX-Video 2B 66 / 70 Decision models run Best: GLiNER2.5 Decide

Models run on the GPU (Vulkan) here, sharing the board’s memory with the system. We plan around 16.0 GB of the 32.0 GB (what the operating system leaves free for a model). Radeon Vega 8 graphics (8 compute units); no NPU. llama.cpp uses it through Vulkan (ROCm doesn’t support this GPU).

More about this hardware

MakerAMD
TypeSingle-board computer or edge AI board
GPU share of memory50% (what the GPU can typically be given for a model)
ChipAMD Ryzen Embedded V1605B
AI acceleratorRadeon Vega 8 graphics (8 compute units); no NPU. llama.cpp uses it through Vulkan (ROCm doesn’t support this GPU).
Boards with this chipUDOO BOLT V8 · UDOO BOLT GEAR
Memory typeDDR4-2400, two SO-DIMM slots (dual channel)
Bandwidth figure38.4 GB/s, the chip’s rated memory speed
Note4-core, 8-thread Ryzen Embedded V1605B, up to 32 GB in two SO-DIMMs, plus an Arduino Leonardo-compatible microcontroller. We assume the GPU can use about half of the RAM. GPU figure from 8 CUs at 1.1 GHz.
Specificationsshop.seco.com

Apps that run models well on the UDOO BOLT V8 (32 GB)

Windows

  1. LemonadeAMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. OllamaOne command with Ollama’s own build of this model.
  4. llama.cppUsually the first to support new model architectures.

Linux

  1. LemonadeAMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. OllamaOne command with Ollama’s own build of this model.
  4. llama.cppUsually the first to support new model architectures.

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

1 product with the UDOO BOLT V8 (32 GB)

Best LLMs for the UDOO BOLT V8 (32 GB)

Quality Model Quant Memory Speed Runs
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4BGoogle Q3_K_M 14.9 GB 13.2 tok/s Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Maple Preview (20B-A1B)DeepGrove Q4_K_M 14.3 GB 25.0 tok/s Runs welltight fit
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. K2 Horizon 7BInstitute of Foundation Models Q6_K 10.5 GB 3.1 tok/s Slow
78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 12BGoogle Q4_K_M 9.8 GB 3.4 tok/s Slow
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. gpt-oss 20BOpenAI MXFP4 14.0 GB 11.6 tok/s Runs welltight fit
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. KAT-Coder V2.5 Dev (35B-A3B)Kuaishou Q2_K 15.9 GB 20.8 tok/s Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Mellum2.1 Thinking (12B-A2.5B)JetBrains Q4_K_M 9.4 GB 15.4 tok/s Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 24B-A2BLiquid AI Q3_K_M 13.8 GB 20.0 tok/s Runs welltight fit
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. GLM-4.7 Flash (30B-A3B)Zhipu AI Q2_K 14.8 GB 20.8 tok/s Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. ERNIE 4.5 21B-A3B ThinkingBaidu Q4_K_M 15.7 GB 12.9 tok/s Runs welltight fit
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Qwen AgentWorld 35B-A3BAlibaba Q2_K 15.9 GB 20.8 tok/s Runs welltight fit
65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. DiffusionGemma 26B-A4B ITGoogle Q3_K_M 14.9 GB 12.6 tok/s Runs welltight fit

Best Image models for the UDOO BOLT V8 (32 GB)

Quality Model Quant Memory Speed Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 4BBlack Forest Labs FP8 10.2 GB 20 s Runs well
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. FLUX 3 Image KleinBlack Forest Labs FP8 12.4 GB 1.9 min Slow
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Z-Image TurboAlibaba (Tongyi) FP8 12.6 GB 50 s Slow
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. ERNIE-Image TurboBaidu FP8 14.5 GB 64 s Slowtight fit
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. FLUX.2 [klein] 9BBlack Forest Labs FP8 11.7 GB 38 s Runs wellencoder unloaded after use
81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Z-ImageAlibaba (Tongyi) Q8 GGUF 13.0 GB 7.3 min Very slow

Best Video models for the UDOO BOLT V8 (32 GB)

Quality Model Quant Memory Speed Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2BLightricks FP8 10.8 GB 8.4 min Runs well
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.1 T2V 1.3BAlibaba FP8 12.8 GB 80.5 min Very slow
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI FP16 14.7 GB 2.0 h Very slowtight fit · encoder unloaded after use
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Bernini-R A14B (video generation + editing)ByteDance FP8 10.7 GB 5.2 h Very slowCPU offload
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. CogVideoX 2BZhipu AI FP8 11.0 GB 20.1 min Slow

Best Decision models for the UDOO BOLT V8 (32 GB)

Quality Model Quant Memory Speed Runs
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. GLiNER2.5 DecideFastino Q8_0 1.2 GB 102 ms Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. GLiClass ModernBERT Large v3Knowledgator F16 1.5 GB 96 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 86MMeta Q8_0 1.0 GB 116 ms Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI Q8_0 2.8 GB 253 ms Runs well
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. OpenAI Privacy FilterOpenAI F16 3.8 GB 15 ms Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. FRIDA-DecisionsSber AI Q8_0 1.7 GB 168 ms Runs well
72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. DeBERTa v3 Large Zero-shot v2.0Moritz Laurer Q8_0 1.2 GB 92 ms Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3Jina AI Q8_0 2.8 GB 253 ms Runs well

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?