AMD· RDNA 2.0

AMD Radeon RX 6650M

VRAM
8 GB
ENTRY-LEVEL
BANDWIDTH
224
GB/S
MODELS Q4
212/428
50%
7B Q4 SPEED
~28
GOOD
▸ MODEL COVERAGE @ Q450% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~66
TOK/S
7B
~28
TOK/S
14B
7.9GB NEEDED
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
8 GB
BANDWIDTH
224 GB/s
FP16 COMPUTE
17.3 TFLOPS
TDP
120W
MEMORY
GDDR6
ARCHITECTURE
RDNA 2.0
STREAM PROCESSORS
1,792
COMPUTE UNITS
28
PCIE
Gen 4 x8
114
FAST MODELS · >30 TOK/S
Real-time chat speed
212
USABLE · >10 TOK/S
Comfortable for all tasks
212
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Radeon RX 6650M (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· 212
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
2212
TOK/S · 7% VRAM
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
1991
TOK/S · 7% VRAM
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
1606
TOK/S · 7% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1475
TOK/S · 7% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
778
TOK/S · 8% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
737
TOK/S · 8% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
653
TOK/S · 8% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
594
TOK/S · 9% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
594
TOK/S · 9% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
594
TOK/S · 9% VRAM
S
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
577
TOK/S · 9% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
569
TOK/S · 9% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
553
TOK/S · 9% VRAM
S
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
398
TOK/S · 10% VRAM
S
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
398
TOK/S · 10% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
398
TOK/S · 10% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
398
TOK/S · 10% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
351
TOK/S · 10% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
351
TOK/S · 10% VRAM
S
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
332
TOK/S · 11% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
332
TOK/S · 11% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
332
TOK/S · 11% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
332
TOK/S · 11% VRAM
S
LFM2 700M0.7B
LFM·125K CTX· CHAT· TOOL_USE
284
TOK/S · 11% VRAM
S
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
257
TOK/S · 12% VRAM
S
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
249
TOK/S · 12% VRAM
S
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
221
TOK/S · 13% VRAM
S
Falcon3-1B1B
FALCON·32K CTX· CHAT
199
TOK/S · 14% VRAM
S
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
199
TOK/S · 14% VRAM
S
InternVL3 1B1B
OTHER·32K CTX· CHAT· VISION
199
TOK/S · 14% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
181
TOK/S · 15% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
166
TOK/S · 15% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
166
TOK/S · 15% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
166
TOK/S · 15% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
166
TOK/S · 15% VRAM
S
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
153
TOK/S · 16% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
153
TOK/S · 16% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
153
TOK/S · 16% VRAM
S
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
153
TOK/S · 16% VRAM
S
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
153
TOK/S · 16% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon RX 6650M.

▸ DEVICE UNDER TEST

AMD Radeon RX 6650M8 GB VRAM.

RADEON RX 6650M SPEC
BRAND
AMD
VRAM
8 GB GDDR6
BANDWIDTH
224 GB/s
FP16 COMPUTE
17.3 TFLOPS
FP32 COMPUTE
8.7 TFLOPS
STREAM PROCESSORS
1,792
TDP
120 W
ARCHITECTURE
RDNA 2.0
▸ AI CAPABILITY
212/ 428 models @ Q4

With 8 GB VRAM and 224 GB/s bandwidth, this GPU handles models up to 10.7B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~26 tok/s.

§ 01TOP MODELS FOR RADEON RX 6650M
212 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
SOLAR-10.7B10.7B7.0 GB1928.2
Falcon3-10B10.3B6.8 GB1938.2
Qwen3.5-9B9.7B6.4 GB2138.3
glm-4-9b9.4B6.2 GB2120.5
gemma-2-9b9.2B6.1 GB2230.2
RecurrentGemma 9B9B6.0 GB2235.0
Qwen 3.5 9B9B6.0 GB2250.6
Yi 1.5 9B9B6.0 GB2230.3
Yi Coder 9B9B6.0 GB2235.8
Bamba 9B v29B6.0 GB2226.1
NVIDIA-Nemotron-Nano-9B-v28.9B5.9 GB2244.2
CodeGemma 7B8.54B5.7 GB2340.2
Qwen2.5-VL-7B8.3B5.6 GB2439.1
LFM2 8B A1B8.3B5.6 GB13324.3
Qwen2-VL 7B8.29B5.6 GB2446.6
Qwen3-8B8.2B5.5 GB2443.3
Granite 3.0 8B8.17B5.5 GB2436.4
Granite 3.1 8B8.17B5.5 GB2438.6
Aya Expanse 8B8B5.4 GB2527.8
Cogito 8B8B5.4 GB2517.2