AMD· RDNA 2.0

AMD Radeon RX 6400

VRAM
4 GB
BUDGET
BANDWIDTH
128
GB/S
MODELS Q4
104/428
24%
7B Q4 SPEED
~16
GOOD
▸ MODEL COVERAGE @ Q424% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~38
TOK/S
7B
3.9GB NEEDED
14B
7.9GB NEEDED
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
4 GB
BANDWIDTH
128 GB/s
FP16 COMPUTE
7.1 TFLOPS
TDP
53W
MEMORY
GDDR6
ARCHITECTURE
RDNA 2.0
STREAM PROCESSORS
768
COMPUTE UNITS
12
PCIE
Gen 4 x4
MSRP
$139
93
FAST MODELS · >30 TOK/S
Real-time chat speed
104
USABLE · >10 TOK/S
Comfortable for all tasks
104
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Radeon RX 6400 (or anything bigger) without committing. Pay by the second, cancel anytime.

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 104
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
1264
TOK/S · 14% VRAM
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
1138
TOK/S · 14% VRAM
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
918
TOK/S · 14% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
843
TOK/S · 14% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
444
TOK/S · 16% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
421
TOK/S · 16% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
373
TOK/S · 17% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
340
TOK/S · 17% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
340
TOK/S · 17% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
340
TOK/S · 17% VRAM
S
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
330
TOK/S · 17% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
325
TOK/S · 18% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
316
TOK/S · 18% VRAM
S
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
228
TOK/S · 20% VRAM
S
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
228
TOK/S · 20% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
228
TOK/S · 20% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
228
TOK/S · 20% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
200
TOK/S · 21% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
200
TOK/S · 21% VRAM
S
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
190
TOK/S · 21% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
190
TOK/S · 21% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
190
TOK/S · 21% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
190
TOK/S · 21% VRAM
S
LFM2 700M0.7B
LFM·125K CTX· CHAT· TOOL_USE
163
TOK/S · 23% VRAM
S
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
147
TOK/S · 24% VRAM
S
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
142
TOK/S · 24% VRAM
S
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
126
TOK/S · 26% VRAM
S
Falcon3-1B1B
FALCON·32K CTX· CHAT
114
TOK/S · 27% VRAM
S
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
114
TOK/S · 27% VRAM
S
InternVL3 1B1B
OTHER·32K CTX· CHAT· VISION
114
TOK/S · 27% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
103
TOK/S · 29% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
95
TOK/S · 31% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
95
TOK/S · 31% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
95
TOK/S · 31% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
95
TOK/S · 31% VRAM
S
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
88
TOK/S · 32% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
88
TOK/S · 32% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
88
TOK/S · 32% VRAM
S
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
88
TOK/S · 32% VRAM
S
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
88
TOK/S · 32% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon RX 6400.

▸ DEVICE UNDER TEST

AMD Radeon RX 64004 GB VRAM.

RADEON RX 6400 SPEC
BRAND
AMD
VRAM
4 GB GDDR6
BANDWIDTH
128 GB/s
FP16 COMPUTE
7.1 TFLOPS
FP32 COMPUTE
3.6 TFLOPS
STREAM PROCESSORS
768
TDP
53 W
ARCHITECTURE
RDNA 2.0
MSRP
$139
▸ AI CAPABILITY
104/ 428 models @ Q4

With 4 GB VRAM and 128 GB/s bandwidth, this GPU handles models up to 4.7B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~15 tok/s.

§ 01TOP MODELS FOR RADEON RX 6400
104 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Qwen3.5-4B4.7B3.4 GB2429.3
InternLM2 5B4.5B3.2 GB2547.6
Gemma 3 4B4.3B3.1 GB2622.8
TranslateGemma 4B4B2.9 GB285.5
MedGemma 1.5 4B4B2.9 GB285.5
Qwen 1.5 4B4B2.9 GB2812.6
Qwen3 4B4B2.9 GB2840.7
Qwen 3.5 4B4B2.9 GB2847.4
Qwen3-VL 4B Instruct4B2.9 GB2826.6
Qwen3-Embedding 4B4B2.9 GB28
Nemotron 3 Nano 4B3.97B2.9 GB2932.0
Phi-3.5 Mini 3.8B3.82B2.8 GB3046.6
phi-3-mini-4k 3.8B3.8B2.8 GB3030.5
Phi-4-mini 3.8B3.8B2.8 GB3049.0
Qwen2.5-VL-3B3.8B2.8 GB3029.9
Jina Embeddings v43.8B2.8 GB30
granite-4.0-h-micro 3.2B3.2B2.4 GB3618.4
Llama-3.2-3B3.2B2.4 GB3617.9
Falcon3-3B3.1B2.4 GB3725.7
Qwen 2.5 3B3.1B2.4 GB3737.2