Skip to content
Local AI Wizard
Your machine
Theme

Legion Pro 7i Gen 10 (16IAX10H) · MTM 83F50005US

Lenovo · Legion Pro 7i Gen 10 (16IAX10H)

Laptops24 GB VRAM + 64 GB system RAM

129 text models run well · 896 GB/s bandwidth

Models on this hardware

Start here

Text

Within 24 GB: 129 run well · 7 tight · 28 reviewed · 55 more run slowly (24 of them run well with 32 GB)

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. All 24 text models that would run well with 32 GB but not here already run here, slowly.
Text models that run well within 24 GB
Smaug MiniAbacus AI · 27BQ4 · published params · source76.9Not on the LMArena text leaderboard of 2026-10-22~23 GBTight fit: Needs ~23 GB: runs well, about 1 GB left beyond the system reserveQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · LMArena 1,437Q4 · published params · source75.31,437 ± 5~23 GBTight fit: Needs ~23 GB: runs well, about 1 GB left beyond the system reserveQ4 · published paramssource
Qwen3.6 27BAlibaba · 27BQ4 · published params · source64.0Not on the LMArena text leaderboard of 2026-10-22~23 GBTight fit: Needs ~23 GB: runs well, about 1 GB left beyond the system reserveQ4 · published paramssource
Qwen3 14BAlibaba · 14.8BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~14 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · LMArena 1,437Q4 · published params · sourceNo comparable published result1,437 ± 7~21 GBQ4 · published paramssource
Qwen3 8BAlibaba · 8.2BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~9 GBQ4 · published paramssource
Qwen3.5 9BAlibaba · 9BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~9 GBQ4 · published paramssource
gpt-oss-20bOpenAI · 21B · LMArena 1,317Q4 · published params · sourceNo comparable published result1,317 ± 6~18 GBQ4 · published paramssource
8 of 136

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 2.4 GB free beyond the 2 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 (28 run well, 9 slowly); 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 Legion Pro 7i Gen 10 (16IAX10H) · MTM 83F50005US
Qwen3 14BAlibaba · 14.8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~14 GB9.0Apache 2.010.4M
Gemma 4 26B A4BGoogle · 25.2BNot in LiveBench 2026-06-251,437~21 GB16.9Apache 2.08.2M
Qwen3 8BAlibaba · 8.2BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~9 GB5.0Apache 2.08.1M
Qwen3.5 9BAlibaba · 9BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~9 GB5.7Apache 2.06.1M
gpt-oss-20bOpenAI · 21BNot in LiveBench 2026-06-251,317~18 GB11.6Apache 2.05.8M
Llama 3.1 8B InstructMeta · 8BNot in LiveBench 2026-06-251,211~8 GB4.9Llama 3.14.8M
Qwen3 1.7BAlibaba · 1.7BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~4 GB1.1Apache 2.04.1M
Gemma 4 E4BGoogle · 8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~8 GB5.0Apache 2.04M
8 of 37
Also runs slowly46 models

Above the 24 GB of VRAM, the layers that do not fit run on the CPU from PC RAM, up to 80 GB in all (listed RAM: 64 GB). Planning estimate, not a speed figure. The 9 reviewed models that run slowly are in the table above.

6 of 46

Browse Text models

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

Vision

Within 24 GB: 126 run well · 7 tight · 8 reviewed · 13 more run slowly (9 of them run well with 32 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. All 9 vision models that would run well with 32 GB but not here already run here, slowly.
Vision models that run well within 24 GB
Qwen3.8 27BAlibaba · 27B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 8~23 GBTight fit: Needs ~23 GB: runs well, about 1 GB left beyond the system reserveQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 6~21 GBQ4 · published paramssource
gemma-3-27b-itgoogle · 27.43B · Image to text · LMArena 1,160Q4 · Hugging Face count · source1,160 ± 8~23 GBTight fit: Needs ~23 GB: runs well, about 1 GB left beyond the system reserveQ4 · Hugging Face countsource
Molmo2-8Ballenai · 8.7B · Image to text · LMArena 1,112Q4 · Hugging Face count · source1,112 ± 20~9 GBQ4 · Hugging Face countsource
Qwen2-VL-7B-InstructQwen · 8.29B · Image to text · LMArena 1,031Q4 · Hugging Face count · source1,031 ± 11~9 GBQ4 · Hugging Face countsource
Molmo-7B-D-0924allenai · 8B · Image to text · LMArena 994Q4 · Hugging Face count · source994 ± 14~8 GBQ4 · Hugging Face countsource
Llama-3.2-11B-Vision-Instructmeta-llama · 10.7B · Image to text · LMArena 993Q4 · Hugging Face count · source993 ± 11~11 GBQ4 · Hugging Face countsource
MiniCPM-V-2_6openbmb · 8.1B · Image to text · LMArena 962Q4 · Hugging Face count · source962 ± 16~9 GBQ4 · Hugging Face countsource
8 of 133

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 2.4 GB free beyond the 2 GB the system keeps (the memory figure already includes that reserve).

Also runs slowly13 models

Above the 24 GB of VRAM, the layers that do not fit run on the CPU from PC RAM, up to 80 GB in all (listed RAM: 64 GB). Planning estimate, not a speed figure.

6 of 13

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

Image

53 within 24 GB · 11 more with 32 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 24 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
ERNIE ImageBaidu · 8B · Text to imagePublisher minimum · CUDA · sourceNo comparable published resultNot on the LMArena text-to-image leaderboard of 2026-10-07~24 GBPublisher minimumCUDA · source
ERNIE Image TurboBaidu · 8.03B · Text to imagePublisher minimum · CUDA · sourceNo comparable published resultNot on the LMArena text-to-image leaderboard of 2026-10-07~24 GBPublisher minimumCUDA · source
FLUX.2 [dev]Black Forest Labs · 32B · Image to image · LMArena 1,146Conditional path · CUDA · sourceNo comparable published result1,146 ± 4~24 GBConditional pathCUDA · source
HiDream-O1-Image-Dev-2604HiDream-ai · 8.8B · Text + image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~24 GB16-bit est. · paramssource
HunyuanImage-2.1Tencent Hunyuan · 17B · Text to imageConditional path · CUDA · sourceNo comparable published resultNot on the LMArena text-to-image leaderboard of 2026-10-07~24 GBConditional pathCUDA · source
Ideogram 4.0Ideogram · 9.3B · Text to imageConditional path · CUDA · sourceNo comparable published resultArena rated only the Quality preset (ideogram-4.0-quality); this entry is Ideogram 4.0 without a named preset~24 GBConditional pathCUDA · source
8 of 53

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

With 32 GB you also run… 11

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

6 of 11

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

Video

30 within 24 GB · 4 more with 32 GB
Video models within 24 GB
Wan2.2-TI2V-5BWan-AI · 5B · Text to videoConditional path · CUDA · source~24 GBConditional pathCUDA · source
Wan2.2-TI2V-5B-DiffusersWan-AI · 5B · Text to videoConditional path · CUDA · source~24 GBConditional pathCUDA · source
HunyuanVideo-1.5tencent · 8.3B · Text to video16-bit est. · params · source~22 GB16-bit est. · paramssource
CogVideoX-5b-I2Vzai-org · 5.6B · Image to video16-bit est. · params · source~16 GB16-bit est. · paramssource
CogVideoX1.5-5Bzai-org · 5.6B · Text to video16-bit est. · params · source~16 GB16-bit est. · paramssource
CogVideoX1.5-5B-I2Vzai-org · 5.6B · Image to video16-bit est. · params · source~16 GB16-bit est. · paramssource
SANA-Video_2.0_5B_720pEfficient-Large-Model · 4.5B · Text to video16-bit est. · params · source~13 GB16-bit est. · paramssource
Kandinsky-6.0-Lite-distill-5s-Diffuserskandinskylab · 3.2B · Image to video16-bit est. · params · source~10 GB16-bit est. · paramssource
8 of 30

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

With 32 GB you also run… 4

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

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

Audio

128 within 24 GB · 4 more with 32 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 24 GB
Whisper large-v3-turboOpenAI · 0.81B · Speech to textPlatform path documented · whisper.cpp / CUDA · source7.83Documented path without a memory figurePlatform path documentedwhisper.cpp / CUDA · source
Whisper large-v3OpenAI · 1.55B · Speech to textPlatform path documented · whisper.cpp / CUDA · source7.44Documented path without a memory figurePlatform path documentedwhisper.cpp / CUDA · source
Fish Audio S2 ProFish Audio · 4B · Text to speechPublisher minimum · CUDA · sourceNo comparable published result~24 GBPublisher minimumCUDA · source
MiniMax-Music3MiniMaxAI · 2.4B · Sound effects and audioPublisher minimum · CUDA · sourceNo comparable published result~24 GBPublisher minimumCUDA · source
Llasa-8BHKUSTAudio · 8.6B · Text to speech16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
MOSS-TTS-v1.5OpenMOSS-Team · 8.5B · Text to speech16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
personaplex-7b-v1nvidia · 8.4B · Speech to speech / audio to audio16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
Qwen2-Audio-7B-InstructQwen · 8.4B · Speech to text16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
8 of 128

With 32 GB you also run… 4

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

90 run well within 24 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 24 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 90

Browse Embeddings models

Runs well within 24 GB of VRAM · planning estimates, not measured speed bundled catalog copy · 1,777 repositories · checked

Measurements

Published tokens per second, exactly as measured; never estimated.

Published measurements on this hardware
Llama 2 7B Q4_0Llama 2 7B Q4_0 (scoreboard model; the scor…NVIDIA GeForce RTX 5090 Laptop · 24 GB GDDR7 (the scoreboard names the GPU, not the machine or its power limit)158.14 ± 4.70Q4_0
0 / 128 · Single llama-bench process;…
CUDA
llama.cpp commit 29f1482
Flash Attention enabled
llama.cpp CUDA scoreboard · community result
2026-10-25
Llama 2 7B Q4_0Llama 2 7B Q4_0 (scoreboard model; the scor…Nvidia RTX 5090 Mobile · 24 GB (memory size not stated by the source; this chip is sold with one memory size) · coopmat2154.31 ± 1.61Q4_0
0 / 128 · Single llama-bench process;…
Vulkan
llama.cpp commit 4bc272f
Flash Attention enabled
llama.cpp Vulkan scoreboard · community result
2026-10-25

Specifications

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

GPU VRAM24 GBDedicated · what models load into · source
System RAM64 GBInstalled · not added to VRAM · source
Memory bandwidth896 GB/sManufacturer spec · not model speed · source
Where to buyLenovo.comManufacturer link · choose the configuration there · US · recorded

Markers: the best LiveBench-scored text model that runs well here, and the lightest text model that does not run well here but runs well with 32 GB. Q4 planning estimates, not measured fits.

Reviewed · Manufacturer source

CPU cores
24
Processor
Intel Core Ultra 9 275HX
Graphics processor
NVIDIA GeForce RTX 5090 Laptop GPU
GPU runtime status
Not stated by the source
Memory capacity
64 GB
Memory kind
System RAM
AI performance (TOPS, manufacturer)
1,824 TOPS
Announced
2025-04-10
Battery capacity
99.9 Wh
Bluetooth
Bluetooth 5.4
GPU boost clock
2,160 MHz
CPU efficiency cores
16
CPU performance cores
8
CPU threads
24
CUDA cores
10,496
Dimensions (mm)
364.38 × 275.94 × 21.9–26.65 (W × D × H)
Display color
100% DCI-P3
Display size
16 in
Peak display brightness
1,100 nits
Display refresh rate
240 Hz
Display resolution
2560 x 1600 (WQXGA) OLED
Ethernet
2.5 Gb/s
Form factor
Laptop, 16-inch gaming
GPU VRAM
24 GB
GPU memory type
GDDR7
GPU power
175 W
Graphics type
Discrete NVIDIA GPU (plus Intel integrated graphics in the CPU)
Included power adapter
400 W
Installed storage
2x 1TB SSD M.2 2242 PCIe 4.0x4 NVMe
Installed storage
2,000 GB
Manufacturer part number
83F50005US
Maximum supported memory
64 GB
Memory interface
256 bit
Memory data rate
6,400 MT/s
Installed memory modules
2
Memory slots
2
System memory type
DDR5 CSODIMM
Operating system
Windows 11 Home, English
Ports
2 × USB-A 5 Gbps · 1 × USB-A 10 Gbps (Always On) · 1 × USB-C 10 Gbps (USB PD 95-100 W, DisplayPort 2.1) · 1 × Thunderbolt 4 / USB4 40 Gbps · HDMI 2.1 (up to 8K/60Hz) · 3.5 mm audio combo · 2.5GbE RJ-45 · Slim-tip power connector
Region
NA · USA
Weight
2.57 kg
Wi-Fi
Wi-Fi 7 (802.11be) 2x2
Introduced
2025

Family specification

Checked · Manufacturer source

NPU performance
13 TOPS · INT8

Intel Core Ultra 9 275HX · NVIDIA GeForce RTX 5090 Laptop GPU with 64 GB installed system RAM and 24 GB dedicated GPU VRAM. Runtime support and local inference speed are not verified.

Photo: Lenovo 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; 2 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 (VRAM); each page lists the models that fit it.