Kingy AI · Local AI hardware verdicts · Standard v0.1
Can You Run It at Home?
Kingy’s verdict for each model on six common machine types, from a 16GB laptop to a 512GB Mac Studio. Every verdict names the exact version and says how Kingy knows: measured, reported by a named third party, or estimated.
Estimated verdicts are calculated, not run. Kingy works them out from published file sizes and memory bandwidth, and labels them “(estimated)”. A measured or reported result always wins over an estimate.
24 verdicts for 4 models: 1 Kingy measured · 10 Reported · 10 Estimated · 3 No evidence yet. Data updated Oct 18, 2026.
Every verdict
Each model’s line is for its most common machine type. Select a cell for the detail behind it.
DeepSeek V4.1 Flash 1017
Text model · DeepSeek · Official release: MXFP4 experts + FP8 E4M3 dense/Engram, UE8M0 scales
Can you run DeepSeek V4.1 Flash 1017 at home? Barely. 512GB Mac Studio · DS4 GGUF, MXFP4 + Q8_0; Engram on SSD · ds4-metal main @ 24e30c0 · 37.6 tok/s at 8K context · Reported Oct 18, 2026
Read Kingy’s full DeepSeek V4.1 Flash 1017 postData (JSON)
MiniMax H3
Video model · MiniMax · Official release: BF16 (H3-Base FL2VA and Ref2VA)
Can you run MiniMax H3 at home? Barely. PC with a 24GB GPU · FP8 scaled, pruned (ComfyUI build) · ComfyUI 0.30.0 · 5.5 min per 5 s clip at 1344x768 (124 frames), cold start · Reported Aug 7, 2026
Read Kingy’s full MiniMax H3 postData (JSON)
Qwen3.8-27B
Text model · Qwen (Alibaba) · Official release: BF16 (Qwen also publishes Qwen/Qwen3.8-27B-FP8)
Can you run Qwen3.8-27B at home? Yes. PC with a 24GB GPU · Q4_K_M · llama.cpp b10453, commit 3cb7ffb · 49.1 tok/s · Kingy measured Aug 17, 2026
Read Kingy’s full Qwen3.8-27B postData (JSON)
Qwen3.8-Flash-Next
Text model · Qwen (Alibaba) · Official release: BF16 and FP8 (E4M3, 128x128 blocks); both official
Can you run Qwen3.8-Flash-Next at home? Barely (estimated). PC with a 24GB GPU · GGUF Q2_0 (GSQ-RCO) · llama.cpp mainline with qwen4exp · 22.2 tok/s at 8K context · Estimated Oct 18, 2026
Read Kingy’s full Qwen3.8-Flash-Next postData (JSON)
How Kingy decides
Every verdict follows Kingy’s “Can you run it at home?” standard v0.1. A verdict rates one model on one machine type, names the exact version, and always says how Kingy knows.
Text models
| Verdict | What it takes |
|---|
| Yes | Loads entirely in GPU or unified memory, generates at least 20 tokens/s, works at 8K context or more, and starts answering an 8K prompt within 30 seconds. All four must hold. |
|---|
| Yes, but slow | Loads and runs, but generates 5–20 tokens/s, or takes more than 30 seconds to start answering an 8K prompt. |
|---|
| Barely | Runs, but generates under 5 tokens/s, or needs more than 25% of the weights in system RAM (weights read from SSD count too), or fits only at 3-bit or lower, or only with less than 4K context. |
|---|
| No | Will not load on that machine at any published version. |
|---|
Speed is generation speed for one user (batch 1) at the stated context.
Image and video models
Kingy times one standard output: a 5-second clip at the model’s native resolution, or one 1024×1024 image.
| Verdict | One 5-second clip | One image |
|---|
| Yes | 5 min or less | 30 s or less |
|---|
| Yes, but slow | 5–30 min | 30 s to 3 min |
|---|
| Barely | Over 30 min, only at reduced resolution or length, or with heavy offload (ComfyUI partial offload counts) | Over 3 min, or with offload |
|---|
| No | Won’t load | Won’t load |
|---|
Media speed depends too much on compute and pipeline settings to estimate, so media verdicts are always measured or reported. Without either, they read “Not tested yet”.
How Kingy knows
- Kingy measured: Kingy ran it. Each result has a Local Lab receipt with the exact file and hash, runtime build, command, context, speed and date. Failed attempts are kept too.
- Reported: a named third party ran it. Kingy links the report and records their machine, file, runtime and speed. “Runs fine” without numbers does not count.
- Estimated: calculated, not run, from the published file size and the formula below. An estimate always says “(estimated)” and never shows as a bare “Yes”.
- No evidence yet: no measurement, no reliable report and, for text models, no published weight size to estimate from. The verdict is then “Not tested yet”. Kingy never invents a verdict to avoid saying so.
The estimate formula for text models
- Memory needed = weight file size + KV cache at 8K context + 10% overhead.
- It fits if the memory needed is no more than the machine type’s usable memory.
- Speed ≈ 0.5 × memory bandwidth ÷ bytes read per token, where bytes per token = active parameters × bits per weight ÷ 8. Mixture-of-experts models use active, not total, parameters. Real runtimes usually reach 60–80% of bandwidth, so 0.5 errs on the slow side.
- On GPU PCs, if more than 25% of the weights must sit in system RAM, the estimate is Barely at best.
An estimated “Yes” needs at least 40 tokens/s, twice the threshold, and 20% spare memory. Otherwise the best an estimate can say is “Yes, but slow”. An estimated “No” means even the smallest published version is bigger than the machine’s usable memory plus, on GPU PCs, the system RAM. When a measurement and an estimate disagree, the measurement wins.
Machine types
Verdicts are per machine type, not per exact computer. Each type has a reference machine, and estimates use its numbers. Newer chips are often faster, so estimates err on the slow side. GB means 10⁹ bytes.
| Machine type | Reference machine | Memory a model can use | Memory bandwidth |
|---|
| 16GB laptop | MacBook Air M4, 16GB | 10.5 GB (macOS lets the GPU use about 2/3 of RAM) | 120 GB/s |
|---|
| PC with a 24GB GPU | RTX 4090 24GB with 64GB DDR5 system RAM | 22.5 GB VRAM (24 minus 1.5 for driver and display) | 1,008 GB/s GPU · ~80 GB/s system RAM |
|---|
| PC with a 32GB GPU | RTX 5090 32GB with 64GB DDR5 system RAM | 30.5 GB VRAM | 1,792 GB/s GPU · ~80 GB/s system RAM |
|---|
| 64GB Mac | Mac Studio M4 Max, 64GB | 48 GB (macOS default, about 3/4 of RAM) | 546 GB/s |
|---|
| 128GB Mac or Strix Halo PC | Ryzen AI Max+ 395, 128GB (the slower of the two) | 96 GB | 256 GB/s (an M4 Max 128GB is about 2× faster) |
|---|
| 512GB Mac Studio | Mac Studio M3 Ultra, 512GB | 384 GB (macOS default; raising iogpu.wired_limit_mb allows more) | 819 GB/s |
|---|
Exact versions and rechecks
- Every verdict names the file tested or estimated, its format, the runtime, and how it compares with the official release. Local does not automatically mean compressed, and online does not automatically mean full quality.
- Measured and reported verdicts are marked “Recheck due” after 90 days, estimates after 30 days. The old result stays visible until the recheck.