FitMyLLM
▸ QUALCOMM· ADRENO 600

Qualcomm Adreno 619

Running LLMs on the Qualcomm Adreno 619 — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
8 GB
ENTRY-LEVEL
BANDWIDTH
17
GB/S
MODELS Q4
201/449
45%
7B Q4 SPEED
~2
SLOW
▸ MODEL COVERAGE @ Q445% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~5
TOK/S
7B
~2
TOK/S
14B
—
7.9GB NEEDED
32B
—
18.0GB NEEDED
70B
—
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS →
▸ SPECIFICATIONS
VRAM
8 GB
BANDWIDTH
17 GB/s
FP16 COMPUTE
0.4 TFLOPS
TDP
4W
MEMORY
Shared
ARCHITECTURE
Adreno 600
15
FAST MODELS · >30 TOK/S
Real-time chat speed
47
USABLE · >10 TOK/S
Comfortable for all tasks
201
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Qualcomm Adreno 619 (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· 201
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
168
TOK/S · 7% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
112
TOK/S · 7% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
108
TOK/S · 7% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
108
TOK/S · 7% VRAM
›
A
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
59
TOK/S · 8% VRAM
›
A
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
56
TOK/S · 8% VRAM
›
A
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
50
TOK/S · 8% VRAM
›
A
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
45
TOK/S · 9% VRAM
›
A
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
45
TOK/S · 9% VRAM
›
A
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
45
TOK/S · 9% VRAM
›
A
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
43
TOK/S · 9% VRAM
›
A
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
42
TOK/S · 9% VRAM
›
A
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
40
TOK/S · 9% VRAM
›
B
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
30
TOK/S · 10% VRAM
›
B
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
30
TOK/S · 10% VRAM
›
B
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
29
TOK/S · 10% VRAM
›
B
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
27
TOK/S · 10% VRAM
›
B
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
27
TOK/S · 10% VRAM
›
B
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
25
TOK/S · 11% VRAM
›
B
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
25
TOK/S · 11% VRAM
›
B
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
25
TOK/S · 11% VRAM
›
C
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
24
TOK/S · 11% VRAM
›
C
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
20
TOK/S · 12% VRAM
›
C
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
20
TOK/S · 12% VRAM
›
C
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
19
TOK/S · 12% VRAM
›
C
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
17
TOK/S · 13% VRAM
›
C
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
16
TOK/S · 13% VRAM
›
D
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
14
TOK/S · 15% VRAM
›
D
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
14
TOK/S · 14% VRAM
›
D
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
13
TOK/S · 15% VRAM
›
D
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
13
TOK/S · 15% VRAM
›
D
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
13
TOK/S · 15% VRAM
›
D
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
13
TOK/S · 15% VRAM
›
D
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
12
TOK/S · 16% VRAM
›
D
OPT 1.3B1.3B
OPT·2K CTX· CHAT
12
TOK/S · 16% VRAM
›
D
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
12
TOK/S · 16% VRAM
›
D
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
11
TOK/S · 17% VRAM
›
D
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
11
TOK/S · 17% VRAM
›
D
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
11
TOK/S · 16% VRAM
›
D
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
10
TOK/S · 70% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Qualcomm Adreno 619.

WHAT THIS CARD IS WORTH

Qualcomm Adreno 619 holds 201 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is Falcon3-10B at IQ4_XS.

TOKENS/SEC PER $100
—
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
—
what memory costs on this card
THE BIGGEST IT TAKES
Falcon3-10B10.3B · IQ4_XS7.1 GB2 tok/sEST
Bamba 9B v29.78B · Q4_K_M7.2 GB2 tok/sEST
RecurrentGemma 9B9.63B · Q4_K_M6.8 GB2 tok/sEST
glm-4-9b9.4B · Q4_K_M6.6 GB2 tok/sEST
Yi 1.5 9B9B · Q4_K_M6.5 GB2 tok/sEST
Yi Coder 9B9B · Q4_K_M6.5 GB2 tok/sEST
Ministral 3 8B8.92B · Q4_K_M6.6 GB2 tok/sEST
Ministral 3 8B Reasoning8.92B · Q4_K_M6.6 GB2 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M3 Pro (18GB)12 GB$1,5991.5 tok/s per $100
M1 Pro (16GB)11 GB$9992.9 tok/s per $100
M2 Pro (16GB)11 GB$1,2992.2 tok/s per $100
M4 (16GB)11 GB$4994.0 tok/s per $100
Qualcomm Adreno 6198 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

Qualcomm Adreno 619 — 8 GB VRAM.

▸ QUALCOMM ADRENO 619 SPEC
BRAND
Apple
VRAM
8 GB Shared
BANDWIDTH
17 GB/s
FP16 COMPUTE
0.4 TFLOPS
TDP
4 W
ARCHITECTURE
Adreno 600
▸ AI CAPABILITY
201/ 449 models @ Q4

With 8 GB VRAM and 17 GB/s bandwidth, this GPU handles models up to 9.63B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~2 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR QUALCOMM ADRENO 619
201 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
RecurrentGemma 9B9.63B6.4 GB235.0
glm-4-9b9.4B6.2 GB220.5
gemma-2-9b9.2B6.1 GB230.2
Yi 1.5 9B9B6.0 GB230.3
Yi Coder 9B9B6.0 GB235.8
Ministral 3 8B8.92B5.9 GB225.7
Ministral 3 8B Reasoning8.92B5.9 GB2—
NVIDIA-Nemotron-Nano-9B-v28.9B5.9 GB244.2
InternLM3 8B Instruct8.8B5.9 GB238.7
Gemma 1 7B8.54B5.7 GB224.7
CodeGemma 7B8.54B5.7 GB240.2
LFM2 8B A1B8.3B5.6 GB1024.3
Seed-Coder 8B Instruct8.25B5.5 GB234.1
Seed-Coder 8B Reasoning8.25B5.5 GB232.9
DeepSeek R1-0528 Qwen3 8B8.2B5.5 GB236.3
Qwen3-8B8.2B5.5 GB243.3
Granite 3.0 8B8.17B5.5 GB236.4
Granite 3.1 8B8.17B5.5 GB238.6
Command-R7B8.03B5.4 GB235.3
Aya Expanse 8B8B5.4 GB227.8