Will It Run AI
CalculatorModelsHardwareCompare
Product
  • Calculator
  • Compare
  • Tier List
Browse
  • Models
  • Hardware
  • Docs
About
  • Why It Works
  • What's New
  • Legal Notice
  • Privacy Policy

All estimates are approximations based on mathematical models and public specifications. Actual performance may vary. Do not make purchasing decisions based solely on these estimates.

Data sourced from Hugging Face, Ollama, and official model documentation. Model names and logos are trademarks of their respective owners.

© 2026 Will It Run AI — Fase Consulting Ibiza, S.L. (NIF: B57969656)

Home/Hardware/GPUs/RX 7800 XT 16GB
AMD

AMD

RX 7800 XT 16GB

RX 7000ConsumerRDNA 3PCIe 4ROCm
16GB
VRAM
624GB/s
Bandwidth
39TFLOPS
FP16 Compute
312TOPS
INT8 Inference
$499 MSRP
VRAM16 GBBandwidth624 GB/sCompute39 TFInference312 TOPSValue7.82 TF/$k
RX 7800 XT 16GBCategory AvgRTX 4000 Ada 20GB

Specifications

Compute
FP1639 TFLOPS
INT8312 TOPS
ArchitectureRDNA 3
Memory
VRAM16 GB
Bandwidth624 GB/s
General
FamilyRX 7000
SegmentConsumer
InterconnectPCIe 4
Compute PlatformROCM
MSRP$499

Architecture

RDNA 3

RDNA 3 is AMD's chiplet-based GPU architecture, combining a 5nm Graphics Compute Die (GCD) with 6nm Memory Cache Dies (MCDs). It introduces AI accelerators and a new unified compute unit design.

AI Relevance

ROCm support for RDNA 3 is maturing but lags behind NVIDIA's CUDA ecosystem. AI accelerator units provide some inference acceleration, but lack the dedicated Tensor Core equivalent found in NVIDIA GPUs.

Process: TSMC 5nm + 6nmPlatform: ROCMPrecisions: FP32, FP16, BF16, INT8

Recommendations by Workload

Agentic Coding

B

Yi Coder 9B

This model is still usable for agentic-coding, but it is not the most specialized pick. It sits in the middle of the current model mix. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.

Decode 70.5 tok/s · 47K ctx · llama.cpp
10.8 GB / 16.0 GB VRAM

Chat

C

Qwen 3 8B

This model is a direct match for chat. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.

Decode 79.3 tok/s · 16K ctx · llama.cpp
8.2 GB / 16.0 GB VRAM

Coding

C

Yi Coder 9B

This model is still usable for coding, but it is not the most specialized pick. It sits in the middle of the current model mix. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.

Decode 70.5 tok/s · 27K ctx · llama.cpp
9.4 GB / 16.0 GB VRAM

RAG

C

granite 8b code instruct 4k

This model is a direct match for rag. It sits in the middle of the current model mix. It fits natively with comfortable headroom.

Decode 79.3 tok/s · 52K ctx · llama.cpp
9.9 GB / 16.0 GB VRAM

Reasoning

C

Qwen 3 14B

This model is a direct match for reasoning. It belongs to a current frontier family for local AI. It should run, but memory headroom will be limited. Known channels: huggingface, ollama, lm-studio.

Decode 45.3 tok/s · 19K ctx · llama.cpp
13.2 GB / 16.0 GB VRAM

Full Model Compatibility

UnslothQwen3.5 9B
C54
9B9.4 GB71 tok/s27K ctx
dense
HauhauCSHQwen3.5 9B Uncensored HauhauCS Aggressive
C54
9B9.4 GB71 tok/s27K ctx
dense
Lmstudio-communityLQwen3.5 9B
C54
9B9.4 GB71 tok/s27K ctx
dense
BartowskiBMeta Llama 3.1 8B Instruct
C53
8B8.6 GB79 tok/s30K ctx
dense
XtunerXllava llama 3 8b v1 1
C53
8B8.6 GB79 tok/s30K ctx
dense
UnslothDeepSeek R1 0528 Qwen3 8B
C53
8B8.6 GB79 tok/s30K ctx
dense
MaziyarPanahiMMeta Llama 3 8B Instruct
C53
8B8.6 GB79 tok/s30K ctx
dense
TheBlokeTLlama 2 7B Chat
C53
7B7.9 GB91 tok/s33K ctx
dense
TheBlokeTMistral 7B Instruct v0.2
C53
7B7.9 GB91 tok/s33K ctx
dense
MaziyarPanahiMMistral 7B Instruct v0.3
C53
7B7.9 GB91 tok/s33K ctx
dense
UnslothQwen3.5 4B
C50
4B5.7 GB159 tok/s45K ctx
dense
Lmstudio-communityLgemma 3 4b it
C50
4B5.7 GB159 tok/s45K ctx
dense
BartowskiBLlama 3.2 3B Instruct
C50
3B5.5 GB183 tok/s47K ctx
dense
QwenQwen2.5 3B Instruct
C49
3B5.1 GB211 tok/s50K ctx
dense
BartowskiBgemma 2 2b it
C49
2B4.9 GB248 tok/s52K ctx
dense
Googlegemma 2b
C48
2B4.5 GB317 tok/s57K ctx
dense
TheDrummerTGemmasutra Mini 2B v1
C48
2B4.5 GB317 tok/s57K ctx
dense
QwenQwen2.5 1.5B Instruct
C48
1.5B4.2 GB387 tok/s61K ctx
dense
Hugging-quantsHLlama 3.2 1B Instruct Q8 0
C48
1B4.1 GB406 tok/s62K ctx
dense
TheBlokeTTinyLlama 1.1B Chat v1.0
C47
1.1B4.0 GB387 tok/s64K ctx
dense
Ggml-orgGSmolVLM 500M Instruct
C47
0.5B3.7 GB406 tok/s69K ctx
dense
Ggml-orgGembeddinggemma 300M
C47
0.3B3.5 GB406 tok/s72K ctx
dense
DeepSeekDeepSeek R1 671B
F0
671B417.6 GB3 tok/s4K ctx
moe
MistralDevstral 2 123B Instruct
F0
123B96.7 GB5 tok/s4K ctx
dense
Z.aiGLM-5
F0
744B462.6 GB3 tok/s4K ctx
moe
UnslothQwen3.5 27B
F0
27B23.2 GB24 tok/s11K ctx
dense
UnslothQwen3.5 35B A3B
F0
35B29.3 GB18 tok/s9K ctx
dense
Moonshot AIKimi K2.5
F0
1000B617.5 GB2 tok/s4K ctx
moe
MistralMistral Large 3
F0
675B420.7 GB3 tok/s4K ctx
+1moe
MistralMistral Small 4 119B
F0
119B76.1 GB16 tok/s4K ctx
moe
AlibabaQwen3-Coder 30B A3B Instruct
F0
30.5B21.9 GB54 tok/s12K ctx
moe
AlibabaQwen3-Coder 480B A35B Instruct
F0
480B300.8 GB4 tok/s4K ctx
moe
AlibabaQwen3-Coder-Next
F0
80B52.1 GB24 tok/s5K ctx
moe
UnslothQwen3.5 122B A10B
F0
122B81.3 GB6 tok/s4K ctx
dense
DeepSeekDeepSeek V3 671B
F0
671B417.6 GB3 tok/s4K ctx
moe
MistralMixtral 8x22B
F0
141B94.6 GB9 tok/s4K ctx
moe
AlibabaQwen 2.5 72B
F0
72B57.7 GB9 tok/s4K ctx
dense
AlibabaQwen 3 235B A22B
F0
235B149.3 GB7 tok/s4K ctx
moe
AlibabaQwen3-VL 30B A3B Instruct
F0
30B21.6 GB56 tok/s12K ctx
moe
UnslothQwen3.5 397B A17B
F0
397B306.7 GB2 tok/s4K ctx
dense
MistralDevstral Small 2 24B Instruct
F0
24B20.9 GB26 tok/s12K ctx
dense
MetaLlama 3.3 70B
F0
70B56.1 GB9 tok/s5K ctx
dense
MetaLlama 4 Maverick 17B 128E
F0
400B249.2 GB5 tok/s4K ctx
moe
CohereCommand A 111B
F0
111B87.6 GB6 tok/s4K ctx
dense
AlibabaQwen 2.5 Coder 32B
F0
32B27.0 GB20 tok/s9K ctx
dense
AlibabaQwen 2.5 VL 72B
F0
72B57.7 GB9 tok/s4K ctx
dense
Unslothgemma 3 27b it
F0
27B23.2 GB24 tok/s11K ctx
dense
Lmstudio-communityLQwen3.5 35B A3B
F0
35B29.3 GB18 tok/s9K ctx
dense
MistralCodestral 2 25.08
F0
22B19.4 GB29 tok/s13K ctx
dense
MistralDevstral Small 1.1
F0
24B20.9 GB26 tok/s12K ctx
dense

Just out of reach

Models you could run with an upgrade

High-quality models that need a bit more memory

DeepSeekDeepSeek R1 671B
671BTier 5Needs ~423.4 GB
MistralDevstral 2 123B Instruct
123BTier 5Needs ~116.0 GB
Runs on Mac Studio M3 Ultra 256GB
Z.aiGLM-5
744BTier 5Needs ~468.8 GB
UnslothQwen3.5 27B
27BTier 5Needs ~27.4 GB
Runs on RTX 5090 32GB (~$1,999)
UnslothQwen3.5 35B A3B
35BTier 5Needs ~34.8 GB
Runs on Mac mini M4 64GB (~$1,099)

Upgrade paths

Upgrade from RX 7800 XT 16GB

See what you unlock with more powerful hardware

Upgrade options

Upgrade options

NVIDIARTX 4000 Ada 20GBNext step up
20 GB VRAM (+4)
A
Unlocks Qwen3-Coder 30B A3B Instruct, Qwen3-VL 30B A3B Instruct, Codestral 2 25.08+15 more

 

AMDRX 7900 XTX 24GBAMD upgrade
24 GB VRAM (+8)960 GB/s (+336)
B
Unlocks Qwen3.5 27B, Qwen3-Coder 30B A3B Instruct, Qwen3-VL 30B A3B Instruct+32 more · +61% faster avg

~$999 MSRP

AppleMac mini M4 64GBBest value
64 GB Unified (+48)
B
Unlocks Qwen3.5 27B, Qwen3.5 35B A3B, Qwen3-Coder 30B A3B Instruct+51 more

~$1,099 MSRP

AMDAMD Instinct MI350X 288GBBiggest leap
288 GB VRAM (+272)8000 GB/s (+7376)
A
Unlocks Devstral 2 123B Instruct, Qwen3.5 27B, Qwen3.5 35B A3B+81 more · +1071% faster avg

~$8,000 MSRP

Compare this GPU