More
Submit build

Builds / AMD Ryzen AI Max+ 395 (Radeon 8060S iGPU, gfx1151)

Strix Halo (Ryzen AI Max+ 395, 128 GB): Nemotron 3.5 Bolt E4B at 55.5 tok/s on llama.cpp, 96.4 on strix-halo-engine-lab EXL3 with MTP drafter

Last updated:

Source: huggingface.co β†—πŸ“ How measured: reported by the original source; RigBase re-checked the numbers at that source
Legacy models only. Every model measured on this rig now has a newer successor: . The hardware numbers are still a useful reference.
GPU(s)
AMD Ryzen AI Max+ 395 (Radeon 8060S iGPU, gfx1151)
Amazon Β· eBay (used) Β· Newegg
VRAM / unified memory (GB)
128
CPU
AMD Ryzen AI Max+ 395
Amazon Β· eBay (used) Β· Newegg
Motherboard
not stated
RAM
128 GB unified
PSU
not stated
Other
strix-halo-engine-lab (ROCm/HIP, gfx1151, gemma4 family) vs llama.cpp 74a4fb00 reference, same machine and session; greedy decoding, 256-token English chat
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Nemotron 3.5 Bolt E4B legacyQ4_K_M (NVIDIA official 4GB GGUF, 6.18 GB)llama.cpp 74a4fb0055.51,881 @ 8K-token prompt
est. TTFT @8k β‰ˆ 4.4 s (calculated from measured prefill)
context: 256-token chat decode, 1 requestπŸ“ Reference row measured in the same turn as the engine rows; 4 requests 193.3 total, 8 requests 279.9; prefill 2,077 @512, 1,376 @32K
Nemotron 3.5 Bolt E4B legacyQ4_K_M (NVIDIA official 4GB GGUF, 6.18 GB)strix-halo-engine-lab, profile default55.8509 @ 8K-token prompt
est. TTFT @8k β‰ˆ 16.1 s (calculated from measured prefill)
context: 256-token chat decode, 1 requestπŸ“ Drafting off; 4 requests 169.8 total, 8 requests 237.9
Nemotron 3.5 Bolt E4B legacyQ4_K_M (NVIDIA official 4GB GGUF, 6.18 GB) + MTP drafterstrix-halo-engine-lab, profile default91.9not stated⚑ spec-decode (MTP + prompt lookup)context: 256-token chat decode, 1 requestπŸ“ Shipped C1 setting (MTP drafter + prompt lookup), token ids identical to drafting off; the int8-activation 'fast' profile reaches 99.5 (54.0 without drafting)
Nemotron 3.5 Bolt E4B legacyEXL3 M4 4.65 bpw (hyukudan, 9.71 GB download, 2.70 GB read per token)strix-halo-engine-lab, profile quality50.2746 @ 8K-token prompt
est. TTFT @8k β‰ˆ 11.0 s (calculated from measured prefill)
context: 256-token chat decode, 1 requestπŸ“ Drafting off; 4 requests 184.8 total, 8 requests 303.0; prefill 794 @512, 533 @32K
Nemotron 3.5 Bolt E4B legacyEXL3 M4 4.65 bpw (hyukudan) + MTP drafterstrix-halo-engine-lab, profile quality96.4not stated⚑ spec-decode (MTP + prompt lookup)context: 256-token chat decode, 1 requestπŸ“ Shipped C1 setting (MTP drafter + prompt lookup), token ids identical to drafting off

Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 Γ· prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.

Quant publisher's own measurements on the Hugging Face model card (hyukudan, card updated 2 Nov 2026), one measuring session of one engine build. The EXL3 M4 pack loads only in strix-halo-engine-lab. Quality on the same card: EXL3 M4 92.94% top-1 / mean KL 0.0367 vs BF16, official Q4_K_M 87.0% / 0.141. llama.cpp prefills about 2.5x faster than the engine today (the engine's prefill is being optimised).

Source: https://huggingface.co/hyukudan/Nemotron-3.5-Bolt-E4B-EXL3

Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.

Embed this result

Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds β€” numbers stay on the build page.

Markdown

[![Measured on RigBase](https://getrigbase.com/badge/strix-halo-128gb-nemotron-35-bolt-e4b-exl3-q4km-engine-lab-hyukudan.svg)](https://getrigbase.com/builds/strix-halo-128gb-nemotron-35-bolt-e4b-exl3-q4km-engine-lab-hyukudan/)

HTML

<a href="https://getrigbase.com/builds/strix-halo-128gb-nemotron-35-bolt-e4b-exl3-q4km-engine-lab-hyukudan/" rel="noopener"><img src="https://getrigbase.com/badge/strix-halo-128gb-nemotron-35-bolt-e4b-exl3-q4km-engine-lab-hyukudan.svg" alt="Measured on RigBase" height="20"/></a>

Preview: Measured on RigBase Β· How to use

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Speculative-decoding rows on this page are not like-for-like with plain decode. See how much MTP and DFlash really speed things up (measured pairs).