Skip to content
Local AI Wizard
Your machine
Theme

Surface Laptop 13.8-inch (8th Edition) · Snapdragon X2 Elite (12-core) · 64 GB LPDDR5x

Microsoft · Surface Laptop 13.8-inch (8th Edition)

162 text models run well · 152 GB/s bandwidth

Models on this hardware

Start here

Text

Within 64 GB: 162 run well · 29 tight · 37 reviewed

Text · LiveBench · overall

0–100 · higher is better

  • Color = publisher

Source: LiveBench 2026-06-25 · collected 2026-09-26 · Open models without a score are not drawn (no score ≠ 0).

Rows run well first, then tight fits; within each, reviewed models, then Hub downloads over 30 days, not quality. Sort a score column to rank by that source alone. No model runs only partly on this machine: it either fits in its shared memory or it does not. No other text model would run well with 96 GB.
Text models that run well within 64 GB
Smaug MiniAbacus AI · 27BQ4 · published params · source76.9Not on the LMArena text leaderboard of 2026-10-22~29 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · LMArena 1,437Q4 · published params · source75.31,437 ± 5~29 GBQ4 · published paramssource
Qwen3.6 27BAlibaba · 27BQ4 · published params · source64.0Not on the LMArena text leaderboard of 2026-10-22~29 GBQ4 · published paramssource
Qwen3 14BAlibaba · 14.8BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~20 GBQ4 · published paramssource
Gemma 4 31BGoogle · 30.7B · LMArena 1,452Q4 · published params · sourceNo comparable published result1,452 ± 7~32 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · LMArena 1,437Q4 · published params · sourceNo comparable published result1,437 ± 7~27 GBQ4 · published paramssource
Qwen3 8BAlibaba · 8.2BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~15 GBQ4 · published paramssource
Qwen3.5 9BAlibaba · 9BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~15 GBQ4 · published paramssource
8 of 191

LMArena ratings in this table: LMArena 2026-10-22 · collected 2026-10-25 · dataset · CC BY 4.0

Tight fit: it runs, but leaves less than 6.4 GB free beyond the 8 GB the system keeps (the memory figure already includes that reserve).

Every reviewed text model here 37

Every one that runs here, well or slowly, scored or not; 19 of 37 have a LiveBench or LMArena result. Run well first, then tight fits, then slow; within each, by Hub downloads over 30 days, read 2026-10-25, not by quality.

Reviewed text models that run on Surface Laptop 13.8-inch (8th Edition) · Snapdragon X2 Elite (12-core) · 64 GB LPDDR5x
Qwen3 14BAlibaba · 14.8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~20 GB9.0Apache 2.010.4M
Gemma 4 31BGoogle · 30.7BNot in LiveBench 2026-06-251,452~32 GB18.3Apache 2.08.4M
Gemma 4 26B A4BGoogle · 25.2BNot in LiveBench 2026-06-251,437~27 GB16.9Apache 2.08.2M
Qwen3 8BAlibaba · 8.2BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~15 GB5.0Apache 2.08.1M
Qwen3.8 27BAlibaba · 27B75.31,437~29 GB16.5Apache 2.07.8M
Qwen3.5 9BAlibaba · 9BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~15 GB5.7Apache 2.06.1M
gpt-oss-20bOpenAI · 21BNot in LiveBench 2026-06-251,317~24 GB11.6Apache 2.05.8M
Llama 3.1 8B InstructMeta · 8BNot in LiveBench 2026-06-251,211~14 GB4.9Llama 3.14.8M
8 of 37

Browse Text models

Adjust the estimate: quantization, context, reserveloads the live catalog

Vision

Within 64 GB: 142 run well · 1 tight · 10 reviewed · 7 more with 96 GB

Vision · LMArena

rating · higher is better

  • Color = publisher

Source: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0 · Models without a rating are left out, not scored as zero.

Rows run well first, then tight fits; within each, reviewed models, then Hub downloads over 30 days, not quality. Sort a score column to rank by that source alone. No model runs only partly on this machine: it either fits in its shared memory or it does not.
Vision models that run well within 64 GB
Gemma 4 31BGoogle · 30.7B · Image to text · LMArena 1,262Q4 · published params · source1,262 ± 6~32 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 8~29 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 6~27 GBQ4 · published paramssource
gemma-3-27b-itgoogle · 27.43B · Image to text · LMArena 1,160Q4 · Hugging Face count · source1,160 ± 8~29 GBQ4 · Hugging Face countsource
Qwen2.5-VL-32B-InstructQwen · 33.45B · Image to text · LMArena 1,119Q4 · Hugging Face count · source1,119 ± 15~34 GBQ4 · Hugging Face countsource
Molmo2-8Ballenai · 8.7B · Image to text · LMArena 1,112Q4 · Hugging Face count · source1,112 ± 20~15 GBQ4 · Hugging Face countsource
Molmo-72B-0924allenai · 73.31B · Image to text · LMArena 1,045Q4 · Hugging Face count · source1,045 ± 13~63 GBTight fit: Needs ~63 GB: runs well, about 1 GB left beyond the system reserveQ4 · Hugging Face countsource
Qwen2-VL-7B-InstructQwen · 8.29B · Image to text · LMArena 1,031Q4 · Hugging Face count · source1,031 ± 11~15 GBQ4 · Hugging Face countsource
8 of 143

LMArena ratings in this table: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0

Tight fit: it runs, but leaves less than 6.4 GB free beyond the 8 GB the system keeps (the memory figure already includes that reserve).

With 96 GB you also run… 7

The next memory size on this ladder runs these well. Figures are the requirement on this hardware type.

6 of 7

12 more vision models in the catalog have no usable memory figure or parameter count for this profile. Browse Vision models

Image

75 within 64 GB · 2 more with 96 GB

Image · Prompt alignment · GenEval

0–1 · higher is better

Source: GenEval · 2023 · reviewed 2026-10-05 · Published quality in the original benchmark preset; not measured on this hardware.

Image models within 64 GB
Stable Diffusion XL 1.0Stability AI · 2.6B · Text to imagePlatform path documented · stable-diffusion.cpp · source0.55Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedstable-diffusion.cpp · source
Stable Diffusion 1.5Stability AI · 0.98B · Text to imagePlatform path documented · stable-diffusion.cpp · source0.43Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedstable-diffusion.cpp · source
Qwen-Image-EditQwen · 20.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
Qwen-Image-Edit-2509Qwen · 20.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
Qwen-Image-Edit-2511Qwen · 20.4B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
Qwen-Image-LayeredQwen · 20.4B · Text + image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~51 GB16-bit est. · paramssource
Qwen-Image-2512Qwen · 20B · Text to image · LMArena 1,12516-bit est. · params · sourceNo comparable published result1,125 ± 3~50 GB16-bit est. · paramssource
HiDream-I1-FullHiDream-ai · 17.1B · Text to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~44 GB16-bit est. · paramssource
8 of 75

LMArena ratings in this table: LMArena 2026-10-07 · collected 2026-10-25 · dataset · CC BY 4.0

With 96 GB you also run… 2

The next memory size on this ladder. Figures are the requirement on this hardware type.

17 more image models in the catalog have no usable memory figure or parameter count for this profile. Browse Image models

Video

59 within 64 GB · 14 more with 96 GB
Video models within 64 GB
LTX-2.3 FastLightricks · 22B · Text to video16-bit est. · params · source~55 GB16-bit est. · paramssource
LTX-2.3 ProLightricks · 22B · Text to video16-bit est. · params · source~55 GB16-bit est. · paramssource
Video-As-Prompt-Wan2.1-14BByteDance · 20.7B · Image to video16-bit est. · params · source~52 GB16-bit est. · paramssource
JoyAI-Echojdopensource · 19B · Image to video16-bit est. · params · source~48 GB16-bit est. · paramssource
LTX-2 FastLightricks · 19B · Text to video16-bit est. · params · source~48 GB16-bit est. · paramssource
LTX-2 ProLightricks · 19B · Text to video16-bit est. · params · source~48 GB16-bit est. · paramssource
LTX-2.5-DiffusersLightricks · 19B · Text to video16-bit est. · params · source~48 GB16-bit est. · paramssource
SkyReels-V3-A2V-19BSkywork · 18.9B · Image to video16-bit est. · params · source~48 GB16-bit est. · paramssource
8 of 59

How this list works Documented execution paths on this hardware first, then publisher minimums (CUDA or Apple MPS).

With 96 GB you also run… 14

The next memory size on this ladder. Figures are the requirement on this hardware type.

6 of 14

20 more video models in the catalog have no usable memory figure or parameter count for this profile. Browse Video models

Audio

133 within 64 GB · 1 more with 96 GB

Audio · Word error rate · Open ASR

% · lower is better

Source: Word error rate · Open ASR · reviewed 2026-10-20 · Published quality in the original benchmark preset; not measured on this hardware.

Audio models within 64 GB
Whisper large-v3-turboOpenAI · 0.81B · Speech to textPlatform path documented · whisper.cpp / CPU · source7.83Documented path without a memory figurePlatform path documentedwhisper.cpp / CPU · source
Whisper large-v3OpenAI · 1.55B · Speech to textPlatform path documented · whisper.cpp / CPU · source7.44Documented path without a memory figurePlatform path documentedwhisper.cpp / CPU · source
Voxtral-Small-24B-2507mistralai · 24.3B · Speech to text16-bit est. · params · sourceNo comparable published result~61 GB16-bit est. · paramssource
Kimi-Audio-7Bmoonshotai · 9.8B · Text to speech16-bit est. · params · sourceNo comparable published result~26 GB16-bit est. · paramssource
Kimi-Audio-7B-Instructmoonshotai · 9.8B · Text to speech16-bit est. · params · sourceNo comparable published result~26 GB16-bit est. · paramssource
AuKtencent · 1.5B · Text to speechConditional path · CUDA · sourceNo comparable published result~25 GBConditional pathCUDA · source
AuK-Flashtencent · Text to speechConditional path · CUDA · sourceNo comparable published result~25 GBConditional pathCUDA · source
Fish Audio S2 ProFish Audio · 4B · Text to speechConditional path · CUDA · sourceNo comparable published result~24 GBConditional pathCUDA · source
8 of 133

With 96 GB you also run… 1

The next memory size on this ladder. Figures are the requirement on this hardware type.

33 more audio models in the catalog have no usable memory figure or parameter count for this profile. Browse Audio models

Embeddings

91 run well within 64 GB

Embeddings · MTEB (Multilingual, v2) · mean(task)

0–100 · higher is better

  • Color = publisher

Source: MTEB results (curated rows, sourced per model)

Embeddings models that run well within 64 GB
Qwen3-Embedding 8BAlibaba (Qwen)8-bit · published params · source70.6~12 GB8-bit · published paramssource
Qwen3-Embedding 4BAlibaba (Qwen)8-bit · published params · source69.5~7 GB8-bit · published paramssource
Harrier OSS v1 (0.6B)Microsoft8-bit · published params · source69.0~3 GB8-bit · published paramssource
Qwen3-Embedding 0.6BAlibaba (Qwen)8-bit · published params · source64.3~3 GB8-bit · published paramssource
Multilingual E5 Large Instructintfloat8-bit · published params · source63.2~3 GB8-bit · published paramssource
EmbeddingGemma 2Google8-bit · published params · source61.4~3 GB8-bit · published paramssource
EmbeddingGemma (300M)Google8-bit · published params · source61.1~3 GB8-bit · published paramssource
BGE-M3BAAI8-bit · published params · source59.6~3 GB8-bit · published paramssource
8 of 91

Browse Embeddings models

Runs well within 64 GB of system RAM · planning estimates, not measured speed bundled catalog copy · 1,777 repositories · checked

Measurements

Speed on this hardware

no published measurement yetWe have not yet included a verifiable measurement for this exact configuration. The memory estimates above do not indicate tokens per second or time to first token.

Specifications

29 sourced fields; the source is named once per group, and a field from another source links to it. Official specifications

System RAM64 GBsystem RAM · CPU planning · source
Memory bandwidth152 GB/sManufacturer spec · not model speed · source
Where to buyMicrosoft StoreManufacturer link · choose the configuration there · US · recorded

Marker: the best LiveBench-scored text model that runs well here. No other text model would run well with 96 GB. Q4 planning estimate, not a measured fit.

Reviewed · Manufacturer source

CPU cores
12
Processor
Qualcomm Snapdragon X2 Elite
Graphics processor
Qualcomm Adreno GPU
GPU runtime status
Not stated by the source
Memory capacity
64 GB
Memory kind
System RAM
Memory bandwidth
152 GB/s
Bluetooth
Bluetooth 5.4
Camera video resolution
1080p Full HD
Dimensions (mm)
301 × 220 × 17.5 (L × W × H)
Display contrast ratio
1300:1
Display size
13.8 in
Peak display brightness
600 nits
Display refresh rate
120 Hz
Display resolution
2304 × 1536
Maximum external displays
3
Form factor
Laptop (clamshell, non-detachable touchscreen)
Included power adapter
39 W
Installed storage
1 TB removable Gen 4 SSD
System memory type
LPDDR5x
NPU performance
80 TOPS · INT8
Operating system
Windows 11 Home
Release date
2026-06-16
Product SKU
Snapdragon® X2 Elite (12 Core), Black, 64GB RAM, 1TB SSD
Installed SSD capacity
1,000 GB
Storage type
Removable solid-state drive (Gen 4 SSD)
Installed memory configuration
LPDDR5x RAM
Wi-Fi
Wi-Fi 7
Introduced
2026

Qualcomm Snapdragon X2 Elite · Qualcomm Adreno GPU with 64 GB installed system RAM for CPU-only planning. Runtime support and local inference speed are not verified.

Photo: Microsoft family photo · memory configuration is not pictured. · Manufacturer source

Memory bandwidth is not measured model speed; verify runtime and checkpoint compatibility. Hardware specification reviewed: 2026-10-18.

How estimates work
Candidates
Reviewed pages use published parameter counts; automatic text candidates use official repository tensor counts (packed quantized weights and unsupported architectures excluded).
Planning
Q4 weights + 20% allowance + reserve: 25% of unified or system memory (at least 2 GB, at most 8 GB; 8 GB here) or 2 GB per dedicated GPU. Adjustable in “Adjust the estimate”. No KV cache is calculated from context.
Fit tiers
Runs well: the estimate fits the fast memory (VRAM, or unified memory within the macOS GPU share). Runs slowly: within the machine's memory but outside the fast part; a graphics card offloads layers to PC RAM (the listed RAM, or 32 GB assumed). Doesn't run: above both. Tiers are planning estimates, never a speed.
Vision
Vision-language models use the Q4 planning estimate from the parameter count (published by the model page, or read from Hugging Face). Classic vision models (classify, detect, segment) use a 16-bit estimate. No vision benchmark is tracked, so rows carry no score.
Media and embeddings
Media rows use documented execution paths (exact hardware or platform) and publisher minimums; a published requirement above this memory moves a model to the next tier. Without either, a 16-bit estimate from the published parameter count (× 1.2 + 2 GB), labelled as such. Embeddings use 8-bit weights + 20% + 2 GB.

Local AI basics: parameters, Q4 and memory · Full model catalog · Data and methodology

Alternatives

Other machines on the same memory ladder (system RAM); each page lists the models that fit it.